© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 11097
    Prev
    Next
    INDEX
    Explanations

    HTML header tags indicating sections 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-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 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
    Enllaços
    -0.76
    Cordialement
    -0.74
    latLng
    -0.72
    Géographie
    -0.72
    mybatisplus
    -0.70
    ssz
    -0.67
    Démographie
    -0.66
     Robles
    -0.66
    Nachteile
    -0.65
     Hàn
    -0.65
    POSITIVE LOGITS
    <h2>
    2.50
    <h1>
    1.32
    <h3>
    1.30
    <th>
    1.26
    <h6>
    1.18
    <h4>
    1.17
    <h5>
    1.12
    <strong>
    1.06
    <b>
    0.88
    <em>
    0.87
    Activations Density 0.004%

    No Known Activations