© 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. 9-GEMMASCOPE-RES-16K
    6. 8706
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to scientific research and discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    news reporting about significant events, discoveries, and announcements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vendas
    -0.30
     Kula
    -0.28
    bahnen
    -0.28
    ージャ
    -0.27
     kull
    -0.27
     angesch
    -0.27
    ViewStyle
    -0.26
    ział
    -0.26
     couro
    -0.26
    ージャー
    -0.26
    POSITIVE LOGITS
    :✨
    0.67
    ագրություններ
    0.65
     CURIAM
    0.63
    UrlResolution
    0.57
     lenker
    0.57
     intStringLen
    0.56
     TAMBÉM
    0.55
     validamos
    0.54
    にほんブログ村
    0.54
     AssemblyTitle
    0.54
    Activations Density 2.099%

    No Known Activations