© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 4970
    Prev
    Next
    INDEX
    Explanations

    opening square bracket tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.58
     RIPRODUZIONE
    -0.49
    __':
    -0.49
     DUTY
    -0.48
     ciudadana
    -0.47
    ']=
    -0.47
    =
    -0.47
    `,
    -0.46
    ')],
    -0.45
    "]=
    -0.44
    POSITIVE LOGITS
     ["
    2.53
     ['
    2.36
    (["
    2.09
    =["
    1.91
    (['
    1.79
    =['
    1.73
    ["
    1.52
     {"
    1.51
     ("
    1.35
    []{"
    1.33
    Activations Density 0.169%

    No Known Activations