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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6827
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between concepts or variables

    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
    MENAFN
    -0.59
    zzleHttp
    -0.52
    rofoam
    -0.48
    uxxxx
    -0.48
    XMLSchema
    -0.48
    خذ
    -0.47
    ựng
    -0.46
    ‍
    -0.46
     chi̍t
    -0.46
    iettivo
    -0.46
    POSITIVE LOGITS
    رشف
    0.68
    CompleteListener
    0.65
     adapts
    0.62
    enumii
    0.61
    httphttps
    0.60
     Anpass
    0.59
    adapted
    0.58
    Adapted
    0.57
    Adapt
    0.57
     adapted
    0.56
    Activations Density 0.851%

    No Known Activations