© 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. 41-GEMMASCOPE-RES-16K
    11. 7014
    Prev
    Next
    INDEX
    Explanations

    variables and mathematical expressions typically used in algorithmic or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ｐ
    -0.76
     Պ
    -0.68
     Pos
    -0.68
     По
    -0.66
     Per
    -0.65
     Π
    -0.64
     Па
    -0.64
     Pla
    -0.63
     Pi
    -0.63
     Par
    -0.62
    POSITIVE LOGITS
    הפ
    0.56
     הפ
    0.52
    pet
    0.48
     pinterest
    0.48
    pac
    0.46
    pun
    0.46
    ぷ
    0.45
    pq
    0.45
    picasso
    0.45
    pausal
    0.44
    Activations Density 2.657%

    No Known Activations