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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 3349
    Prev
    Next
    INDEX
    Explanations

    statements made by officials or spokespeople regarding events and actions, particularly in relation to investigations and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.86
     Efq
    -0.79
    enderror
    -0.75
     epist
    -0.71
     Theodo
    -0.71
     Shakspeare
    -0.70
     mourut
    -0.68
     fût
    -0.68
     semesters
    -0.68
    AndEndTag
    -0.65
    POSITIVE LOGITS
     reportedly
    0.85
     zufolge
    0.85
     szerint
    0.71
    utnik
    0.70
     ModelExpression
    0.69
     reported
    0.69
    ężczy
    0.66
     said
    0.66
    によると
    0.65
     lawmaker
    0.62
    Activations Density 0.635%

    No Known Activations