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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 9769
    Prev
    Next
    INDEX
    Explanations

    URL navigation and action-related commands in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.65
    PMailer
    -0.54
    niego
    -0.52
    djangoproject
    -0.50
     CURLOPT
    -0.50
    LikeLike
    -0.48
    mergeFrom
    -0.48
    CloseOperation
    -0.47
    )),
    
    -0.47
     intptr
    -0.46
    POSITIVE LOGITS
     AspNetCore
    0.61
    +#+
    0.60
     AttributeSet
    0.56
     CWE
    0.56
    তথ্যসূত্র
    0.56
     EconPapers
    0.54
     IMA
    0.54
     RTA
    0.53
     Vesta
    0.53
     FAP
    0.52
    Activations Density 0.083%

    No Known Activations