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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104682
    Prev
    Next
    INDEX
    Explanations

    phrases related to guidelines or instructions regarding various conditions or standards

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

    Plural nouns or categorizing terms that introduce or precede lists, specifications, or examples of items within that category.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     JAXBElement
    -0.51
     Meksiku
    -0.46
    RegressionTest
    -0.45
    Cyfeiriadau
    -0.44
     ExecuteAsync
    -0.43
    transQ
    -0.42
    bufio
    -0.42
    }{*}{}
    -0.41
    ❊
    -0.41
    matorium
    -0.41
    POSITIVE LOGITS
    Hentet
    0.54
     <<<<<<<<<<<<<<
    0.48
    Datuak
    0.47
    CloseOperation
    0.46
    Độ
    0.40
    IsMutable
    0.36
    cuerdo
    0.35
     препратки
    0.34
    Poll
    0.33
    modb
    0.33
    Activations Density 0.339%

    No Known Activations