© 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. 36-GEMMASCOPE-RES-16K
    6. 16023
    Prev
    Next
    INDEX
    Explanations

    references to specific gene symbols or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tear
    -0.41
     protoimpl
    -0.40
    essoa
    -0.39
    webElement
    -0.38
    frontmatter
    -0.38
    horst
    -0.38
    ix
    -0.38
    erson
    -0.38
     plana
    -0.36
    layed
    -0.36
    POSITIVE LOGITS
    AndEndTag
    0.59
     aeruginosa
    0.46
     getP
    0.44
     ब्रेकडाउन
    0.44
     jadx
    0.43
    vician
    0.42
    UseVisualStyle
    0.42
     margiela
    0.42
    Espèce
    0.40
    ੝
    0.40
    Activations Density 0.386%

    No Known Activations