© 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. 36-GEMMASCOPE-RES-16K
    11. 16008
    Prev
    Next
    INDEX
    Explanations

    programming code structures and data processing operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verifyException
    -0.41
    antwoorden
    -0.38
     aikaa
    -0.37
    想到了
    -0.35
     Tiefe
    -0.33
     aikana
    -0.32
     refinance
    -0.31
    zepine
    -0.30
    Chham
    -0.30
     vệ
    -0.29
    POSITIVE LOGITS
     torch
    0.87
    torch
    0.77
     TOR
    0.66
     torches
    0.60
     invokingState
    0.60
    Torch
    0.59
     Torch
    0.59
     torchvision
    0.59
    TOR
    0.58
    exitRule
    0.56
    Activations Density 0.158%

    No Known Activations