© 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. 12-GEMMASCOPE-RES-16K
    11. 8572
    Prev
    Next
    INDEX
    Explanations

    HTML header tags indicating the structure and hierarchy of content in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeografia
    -0.48
     GALERÍA
    -0.48
     mauva
    -0.48
     toalla
    -0.48
    gameserver
    -0.48
    OneToMany
    -0.47
    qtype
    -0.47
     Salgado
    -0.47
     kasarigan
    -0.47
    DeleteCommand
    -0.47
    POSITIVE LOGITS
    <h2>
    2.09
    <h3>
    0.92
    <h1>
    0.87
    __*/
    0.71
    <h6>
    0.71
    /*
    0.69
    <h4>
    0.68
    __(/*!
    0.67
    <h5>
    0.65
     IActionResult
    0.64
    Activations Density 0.151%

    No Known Activations