© 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. 10797
    Prev
    Next
    INDEX
    Explanations

    code structure and programming elements related to functions and data handling

    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
    PerformLayout
    -0.60
    RenderAtEndOf
    -0.60
    balleur
    -0.51
     كومونز
    -0.50
    endcsname
    -0.49
    styleable
    -0.49
    writeFieldEnd
    -0.49
     برانيه
    -0.48
    ViewImports
    -0.46
     AppCompatTheme
    -0.45
    POSITIVE LOGITS
    <eos>
    0.56
    Jeografia
    0.42
     klant
    0.40
    ...@
    0.40
    hésite
    0.40
    gola
    0.40
     напо
    0.39
    isp
    0.38
    Frank
    0.38
    IBLES
    0.37
    Activations Density 0.051%

    No Known Activations