© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10352
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to programming and data structure concepts

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

    programming or compilation

    np_acts-logits-general · gemini-2.0-flash

    Compile, proto, ssh, java, safe zone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    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
     pungkas
    -0.47
     pungkasnya
    -0.47
     afgelopen
    -0.37
     české
    -0.36
     pelbagai
    -0.35
     veřej
    -0.35
     největ
    -0.35
     waż
    -0.35
     ucapnya
    -0.34
     dôle
    -0.34
    POSITIVE LOGITS
    RenderAtEndOf
    0.66
    臈
    0.63
     Balcony
    0.63
     disambiguazione
    0.61
     Eros
    0.60
     Rune
    0.60
     Icarus
    0.60
     Winery
    0.60
     Doll
    0.59
     للاسماء
    0.59
    Activations Density 4.242%

    No Known Activations