Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13486
    Prev
    Next
    INDEX
    Explanations

    occurrences of variable declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jScrollPane
    -0.69
     Fairbanks
    -0.61
     intptr
    -0.58
    ----</
    -0.56
     мәкал
    -0.55
    σχ
    -0.55
    XmlAccessType
    -0.54
    ContentAlignment
    -0.53
    anor
    -0.52
    ellido
    -0.52
    POSITIVE LOGITS
    let
    4.41
    lets
    3.73
    LET
    3.59
     let
    3.46
     Let
    3.15
    Let
    3.11
     LET
    3.06
    LETS
    3.04
     lets
    2.82
    Lets
    2.64
    Activations Density 0.144%

    No Known Activations