© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 444
    Prev
    Next
    INDEX
    Explanations

    elements related to digital dashboard elements and UI components

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

    HTML/XML markup and technical code structure elements.

    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
    êmio
    -0.41
    PullParser
    -0.37
    owie
    -0.36
    Ծանոթ
    -0.35
     Principe
    -0.35
    }^\
    -0.35
     Príncipe
    -0.34
     Schick
    -0.34
    InteropServices
    -0.34
    createStatement
    -0.33
    POSITIVE LOGITS
     board
    2.42
     Board
    2.16
    Board
    2.09
     boards
    2.06
    board
    2.06
     BOARD
    2.03
    BOARD
    1.88
     Boards
    1.84
    boards
    1.79
    Boards
    1.67
    Activations Density 0.230%

    No Known Activations