© 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. 40-GEMMASCOPE-RES-16K
    6. 2216
    Prev
    Next
    INDEX
    Explanations

    elements related to user input and messaging functionality

    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
     /*#__
    -0.49
     whereof
    -0.47
    pyplot
    -0.44
    ibatis
    -0.43
    WireFormatLite
    -0.43
     are
    -0.42
     boll
    -0.42
     miscellaneous
    -0.41
     never
    -0.41
    Felt
    -0.41
    POSITIVE LOGITS
    把
    0.66
    进行
    0.64
    直接
    0.58
     Jerusalén
    0.57
    打
    0.55
     realização
    0.52
    向
    0.52
     Bersama
    0.52
     aisladas
    0.52
    把自己
    0.52
    Activations Density 0.006%

    No Known Activations