© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 13770
    Prev
    Next
    INDEX
    Explanations

    special formatting or structure indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.89
     Majefty
    -0.88
    AutoresizingMask
    -0.81
     ſeveral
    -0.81
     ſche
    -0.81
     Conſ
    -0.80
     Reſ
    -0.80
    ToAction
    -0.78
     ſtate
    -0.77
     Diſ
    -0.77
    POSITIVE LOGITS
    ্দ
    0.57
    EDEFAULT
    0.54
    thenes
    0.53
     Mon
    0.52
    <bos>
    0.52
    yakarta
    0.51
     newOwner
    0.50
      
    0.49
     mon
    0.48
     tạp
    0.48
    Activations Density 0.157%

    No Known Activations