© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13717
    Prev
    Next
    INDEX
    Explanations

    references to musical productions and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "quantum" or relating to physics

    np_acts-logits-general · gemini-2.0-flash

    quantum gravity fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     boneka
    -0.47
    guantes
    -0.47
     slutet
    -0.45
     vrijwilli
    -0.45
     lubang
    -0.45
     borbo
    -0.45
    Confusion
    -0.45
     dumne
    -0.44
    unzione
    -0.44
    WriteAttribute
    -0.44
    POSITIVE LOGITS
     referenties
    0.39
    دانشنامهٔ
    0.38
    Географи
    0.35
    MODO
    0.35
     jadx
    0.34
    tangentMode
    0.33
    SourceChecksum
    0.33
    quelize
    0.33
     newBuilder
    0.32
    FieldBuilder
    0.32
    Activations Density 1.007%

    No Known Activations