© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9983
    Prev
    Next
    INDEX
    Explanations

    references to distinct groups or entities within a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     Chick
    -0.39
    исленность
    -0.39
     Check
    -0.38
     Cast
    -0.38
     scrap
    -0.38
     check
    -0.37
     Sharp
    -0.36
     Sit
    -0.36
     httpClient
    -0.36
     Northern
    -0.35
    POSITIVE LOGITS
    KommentareTeilen
    0.64
     Италијани
    0.63
    posedge
    0.61
     Biôgrafia
    0.60
    /**
    0.57
    masses
    0.56
     masses
    0.55
    httphttps
    0.54
    uxxxx
    0.51
    bootstrapcdn
    0.51
    Activations Density 0.381%

    No Known Activations