© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-GEMMASCOPE-RES-16K
    11. 6488
    Prev
    Next
    INDEX
    Explanations

    HTML header tags and their levels 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 @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    varargin
    -0.65
     Vann
    -0.62
     hasNext
    -0.58
     varargin
    -0.56
     setPassword
    -0.56
     practition
    -0.55
    rail
    -0.54
     Tann
    -0.54
    iotensin
    -0.54
    ApiRequest
    -0.54
    POSITIVE LOGITS
    <h3>
    1.93
    subsection
    0.79
    <h2>
    0.75
    <h1>
    0.59
     Перейти
    0.54
    "]="
    0.49
     Saltar
    0.46
    <td>
    0.46
    (=)
    0.45
     
    0.45
    Activations Density 0.079%

    No Known Activations