© 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. 7-GEMMASCOPE-RES-16K
    11. 13800
    Prev
    Next
    INDEX
    Explanations

    statements and suggestions related to planning and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.72
     erſt
    -0.68
     deſſen
    -0.66
     beſti
    -0.66
    [@BOS@]
    -0.65
    <pad>
    -0.65
    <unused8>
    -0.65
     beſch
    -0.65
    <unused14>
    -0.65
    <unused3>
    -0.65
    POSITIVE LOGITS
     про
    0.34
    ...
    0.34
     احت
    0.32
     hi
    0.31
     bon
    0.30
    ↵
    0.29
     –
    0.29
     PRO
    0.28
     Pro
    0.28
     pi
    0.28
    Activations Density 0.911%

    No Known Activations