© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 111703
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or identifiers related to scientific data and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    S
    -0.47
     
    -0.47
    .
    -0.46
    A
    -0.45
    <h1>
    -0.44
    (
    -0.44
    T
    -0.41
    [
    -0.40
    I
    -0.40
    The
    -0.40
    POSITIVE LOGITS
     surla
    1.28
    ロウィン
    1.18
     témoig
    1.15
    <unused8>
    1.14
    <unused52>
    1.13
    <unused43>
    1.13
    <unused74>
    1.13
    <unused79>
    1.13
    <unused14>
    1.13
    <unused41>
    1.13
    Activations Density 0.058%

    No Known Activations