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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2042
    Prev
    Next
    INDEX
    Explanations

    instances of the word "first" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getItemCount
    -0.57
     programação
    -0.53
     Audiodateien
    -0.52
    cheme
    -0.51
    pleen
    -0.51
     errMsg
    -0.50
    わけで
    -0.50
     statusCode
    -0.50
     Umfang
    -0.50
    debate
    -0.49
    POSITIVE LOGITS
    First
    1.14
     First
    1.13
     FIRST
    1.13
     first
    1.13
    first
    1.09
    FIRST
    1.08
     getFirst
    0.96
    getFirst
    0.89
     firſt
    0.86
     first
    0.84
    Activations Density 0.134%

    No Known Activations