© 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. 14-GEMMASCOPE-RES-16K
    11. 9632
    Prev
    Next
    INDEX
    Explanations

    mathematical notations or symbols indicating complex expressions or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſur
    -0.77
     itſelf
    -0.74
     auffi
    -0.73
    httphttps
    -0.73
     myſelf
    -0.72
    征詢我
    -0.71
    SequentialGroup
    -0.71
     ſei
    -0.71
     שוליים
    -0.69
     propOrder
    -0.68
    POSITIVE LOGITS
    The
    0.53
    item
    0.53
     the
    0.50
    *
    0.47
    __(/*!
    0.47
    cdot
    0.46
     a
    0.42
    <bos>
    0.41
    )
    0.40
    <td>
    0.39
    Activations Density 0.121%

    No Known Activations