© 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. 36-GEMMASCOPE-RES-16K
    11. 9026
    Prev
    Next
    INDEX
    Explanations

    terms associated with characteristics of entities, particularly related to identity and classification

    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
    subTitle
    -0.31
     т
    -0.29
    青
    -0.28
    ‌
    -0.26
    MigrationBuilder
    -0.23
     пре
    -0.23
    ________
    -0.22
    <eos>
    -0.22
    　　
    -0.22
    <h4>
    -0.22
    POSITIVE LOGITS
    <unused43>
    1.15
    <unused41>
    1.14
    <unused51>
    1.13
    <unused74>
    1.13
    <unused42>
    1.13
    <pad>
    1.13
    <unused8>
    1.13
    <unused17>
    1.13
    <unused3>
    1.13
    [@BOS@]
    1.13
    Activations Density 0.653%

    No Known Activations