© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 501
    Prev
    Next
    INDEX
    Explanations

    terms related to weakness or deficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tion
    -0.49
    tions
    -0.45
    ey
    -0.42
    uen
    -0.42
     приходи
    -0.41
    ations
    -0.41
    存
    -0.41
    ng
    -0.41
    ond
    -0.40
    NSString
    -0.40
    POSITIVE LOGITS
    Too
    0.81
     Too
    0.80
     autorytatywna
    0.78
    Excessive
    0.76
     insufficient
    0.76
     too
    0.75
     ſeine
    0.73
     zijne
    0.73
     TOO
    0.73
    <unused14>
    0.73
    Activations Density 0.217%

    No Known Activations