© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 1322
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks in text-based data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hout
    -0.39
     in
    -0.39
     CreateTagHelper
    -0.38
     to
    -0.37
     surely
    -0.37
    OrNil
    -0.37
     zem
    -0.36
     fish
    -0.36
     pic
    -0.36
     f
    -0.36
    POSITIVE LOGITS
    Literatuur
    0.61
     Италијани
    0.58
    ResumeLayout
    0.58
     betweenstory
    0.57
    SEGUIR
    0.55
    berdayakan
    0.54
    Citiți
    0.54
     Offisielt
    0.53
    /***/
    0.52
    parsedMessage
    0.52
    Activations Density 0.625%

    No Known Activations