© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2701
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and constructs

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

    Comes after punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    lists of initials and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     G
    -0.83
    G
    -0.79
     grams
    -0.76
     gas
    -0.74
     GN
    -0.73
     Gas
    -0.73
    Gradient
    -0.72
    gameserver
    -0.71
    Gas
    -0.71
     g
    -0.71
    POSITIVE LOGITS
     betweenstory
    0.49
    Erreferentziak
    0.44
     själ
    0.43
    usercontent
    0.42
    ToLeft
    0.41
    NewUrlParser
    0.40
    ihnach
    0.39
    ofla
    0.39
    setOnItem
    0.38
     enkelte
    0.38
    Activations Density 0.106%

    No Known Activations