© 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. 31-GEMMASCOPE-RES-16K
    6. 9545
    Prev
    Next
    INDEX
    Explanations

    references to vehicle safety features and performance attributes

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

    specific car model names and brand names.

    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
     kwiat
    -0.37
    ʖ
    -0.32
     persoons
    -0.31
     päivä
    -0.31
    QObject
    -0.31
     obowią
    -0.31
     jeruk
    -0.30
     indywidual
    -0.29
     Pflicht
    -0.29
     criatura
    -0.29
    POSITIVE LOGITS
     Ford
    0.90
     BMW
    0.90
     Toyota
    0.85
     Cessna
    0.83
     Nissan
    0.82
     CreateTagHelper
    0.81
     Honda
    0.80
     Chevy
    0.80
     Dodge
    0.79
     Hyundai
    0.79
    Activations Density 0.622%

    No Known Activations