© 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. 16261
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical placement and arrangement

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

    spatial relationships where one object is placed into, onto, or over another.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    InjectAttribute
    -0.68
    OGND
    -0.66
    createStatement
    -0.65
     leaſt
    -0.63
    idlertid
    -0.63
     שוליים
    -0.63
     للاسماء
    -0.63
    modelBuilder
    -0.62
    ⟬
    -0.61
     kasarigan
    -0.61
    POSITIVE LOGITS
    AddHtmlAttribute
    0.34
     the
    0.33
     Nutzung
    0.30
     kwenye
    0.28
     a
    0.27
     Utilizamos
    0.27
     garden
    0.27
     an
    0.26
     bags
    0.25
    lapsible
    0.25
    Activations Density 0.411%

    No Known Activations