© 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. 8694
    Prev
    Next
    INDEX
    Explanations

    elements related to dimensions and layouts for visual representations, specifically in charting contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    orianCalendar
    -0.41
    cerpt
    -0.38
     befri
    -0.36
     berp
    -0.36
     Administrativna
    -0.36
    ❸
    -0.36
     Maske
    -0.35
    łyż
    -0.35
    principalTable
    -0.35
    setEnabled
    -0.34
    POSITIVE LOGITS
    IntoConstraints
    0.81
     size
    0.68
    AutoSize
    0.66
     sizes
    0.65
     width
    0.62
     ukuran
    0.61
    setVerticalGroup
    0.60
    makeConstraints
    0.60
     sizing
    0.59
    CGSize
    0.58
    Activations Density 0.204%

    No Known Activations