© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3190
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to popularity and prevalence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to popularity, trends, and widespread usage.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    descriptions indicating widespread prevalence or popularity—statements that something is commonly used, widely available, frequent, or conserved across many contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    text describing things that have become popular, common, or widely used/adopted.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esía
    -0.42
    PerformLayout
    -0.40
     createSlice
    -0.39
     MainAxisSize
    -0.37
    NameInMap
    -0.35
    StoryboardSegue
    -0.33
    CreateMap
    -0.33
     Paused
    -0.33
     afternoon
    -0.32
    WebElementEntity
    -0.32
    POSITIVE LOGITS
     Widely
    0.56
     widespread
    0.55
     widely
    0.55
     широко
    0.47
     usarlo
    0.46
     popularity
    0.46
     Used
    0.46
     USED
    0.46
    广泛
    0.45
    Used
    0.45
    Activations Density 0.468%

    No Known Activations