© 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. 21-GEMMASCOPE-RES-16K
    6. 13827
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to quantum mechanics and thermodynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intervals
    -0.40
     interval
    -0.38
     endregion
    -0.37
    REG
    -0.35
     soft
    -0.35
    いいのか
    -0.35
     Sof
    -0.35
     sof
    -0.34
    yb
    -0.33
     Coalition
    -0.33
    POSITIVE LOGITS
    httphttps
    0.68
    MLLoader
    0.66
    extAlignment
    0.57
    Tembelea
    0.56
    ThemeOverlay
    0.52
    SequentialGroup
    0.52
    hyrchwyd
    0.51
    InjectAttribute
    0.49
     AssemblyVersion
    0.49
    RenderAtEndOf
    0.48
    Activations Density 2.398%

    No Known Activations