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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14640
    Prev
    Next
    INDEX
    Explanations

    scientific and technical identifiers, such as publication references and data tables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.87
    tagHelperRunner
    -0.83
     تضيفلها
    -0.82
    <unused30>
    -0.82
    <unused76>
    -0.81
    <unused43>
    -0.81
     ſelb
    -0.81
    <pad>
    -0.81
    <unused6>
    -0.80
    <unused42>
    -0.80
    POSITIVE LOGITS
    /
    0.35
    AppMethodBeat
    0.29
    <
    0.26
     development
    0.25
     
    0.25
    jahr
    0.24
     D
    0.24
    '
    0.23
    <h2>
    0.22
     otherwise
    0.22
    Activations Density 0.817%

    No Known Activations