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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 16102
    Prev
    Next
    INDEX
    Explanations

    document sections that begin with formatted tags or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ErrIntOverflow
    -0.59
    wpa
    -0.59
    PLAN
    -0.58
    czes
    -0.56
     contactez
    -0.56
    urization
    -0.55
    comers
    -0.55
     jScrollPane
    -0.55
     Margar
    -0.55
     Sef
    -0.54
    POSITIVE LOGITS
    DebuggerNonUser
    0.96
    <bos>
    0.74
     Ngb
    0.61
     typelib
    0.59
    SequentialGroup
    0.59
    //
    0.58
    addGap
    0.58
    جستارهای
    0.57
     guma
    0.56
    OGND
    0.55
    Activations Density 0.158%

    No Known Activations