© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15561
    Prev
    Next
    INDEX
    Explanations

    sentences that contain structural descriptions or specifications

    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
     Roskov
    -0.43
     validated
    -0.41
     damit
    -0.38
    WindowConstants
    -0.37
    ricultural
    -0.36
    MÉ
    -0.36
    migrationBuilder
    -0.36
     thứ
    -0.35
    სქოლიო
    -0.35
     parado
    -0.35
    POSITIVE LOGITS
    CppMethod
    0.63
    featureID
    0.56
    Aholisi
    0.47
     насељу
    0.47
    ByExample
    0.47
    execSQL
    0.45
    IsMutable
    0.44
    itinéraire
    0.43
     groupBox
    0.42
     typelib
    0.42
    Activations Density 0.135%

    No Known Activations