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. 4-GEMMASCOPE-RES-16K
    6. 3443
    Prev
    Next
    INDEX
    Explanations

    suggestions or recommendations regarding actions to take

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     усе
    -0.57
    IsContent
    -0.53
    minecraft
    -0.52
     caractère
    -0.52
     mouths
    -0.49
    cademia
    -0.48
    tuale
    -0.48
    InvalidProtocol
    -0.48
    Reaching
    -0.48
     بلکه
    -0.48
    POSITIVE LOGITS
     sebaiknya
    0.77
    ควร
    0.74
     preferably
    0.74
     gärna
    0.73
     advisable
    0.73
     should
    0.72
     bör
    0.70
    hould
    0.69
     sollten
    0.69
     devriez
    0.67
    Activations Density 0.406%

    No Known Activations