© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8379
    Prev
    Next
    INDEX
    Explanations

    function definitions and return statements in programming code

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

    Code snippets containing "System" or "tft"

    np_acts-logits-general · gemini-2.0-flash

    ring where

    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
    NewUrlParser
    -0.63
     bless
    -0.58
    glGet
    -0.58
    BindingResult
    -0.58
    Koordinaten
    -0.56
    FetchType
    -0.56
     getchar
    -0.56
     متعلقه
    -0.56
    紆
    -0.55
     Wicidata
    -0.51
    POSITIVE LOGITS
    AndEndTag
    0.83
     StringBuilder
    0.77
    StringBuilder
    0.77
     tartalomajánló
    0.71
    tonsoft
    0.59
    StringBuffer
    0.57
    stringstream
    0.56
    polated
    0.53
     الحره
    0.52
     StatelessWidget
    0.52
    Activations Density 0.094%

    No Known Activations