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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2942
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values related to layout and positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    CSS and HTML markup with property declarations and styling attributes.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Deum
    -0.49
    Lähteet
    -0.49
     ligiloj
    -0.43
     objectForKey
    -0.42
     croce
    -0.42
     Thin
    -0.42
    Thin
    -0.41
    scriptcase
    -0.41
     professionally
    -0.41
     Slab
    -0.41
    POSITIVE LOGITS
     top
    0.76
    top
    0.67
     position
    0.66
     bottom
    0.65
     positioned
    0.62
     left
    0.62
    Positioned
    0.60
     POSITION
    0.59
     ubic
    0.59
     Position
    0.59
    Activations Density 0.217%

    No Known Activations