© 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. 8926
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their experiences in racing

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

    specific names of racing drivers and motorsport competitors.

    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
    intios
    -0.36
    Derp
    -0.34
     "..\..\
    -0.34
    IUrlHelper
    -0.33
     Equipo
    -0.33
    口碑
    -0.31
    berdayakan
    -0.31
     transférez
    -0.31
     diversification
    -0.31
     esprit
    -0.31
    POSITIVE LOGITS
     lap
    0.64
     الحره
    0.54
    IVEREF
    0.53
     overtaking
    0.52
     laps
    0.51
     overheating
    0.50
    SharedCtor
    0.49
     overtake
    0.48
    laps
    0.47
     rejoined
    0.47
    Activations Density 0.075%

    No Known Activations