Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8054
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to CSS styling

    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
     BigInteger
    -0.53
     EntityManager
    -0.52
     totalCount
    -0.51
     WaitForSeconds
    -0.50
    reportWebVitals
    -0.46
    xFFFFFFFF
    -0.46
     Gibbons
    -0.46
     rodilla
    -0.46
    gabriel
    -0.45
     cuantos
    -0.45
    POSITIVE LOGITS
     Style
    1.28
     STYLE
    1.27
    Style
    1.23
     style
    1.18
    style
    1.14
    STYLE
    1.13
     Styles
    1.02
    estyle
    1.02
     styles
    0.95
     Estilo
    0.94
    Activations Density 0.049%

    No Known Activations