© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 79063
    Prev
    Next
    INDEX
    Explanations

    references to highways and related infrastructure

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

    highway and related infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.42
    د
    -0.38
    coloured
    -0.37
    Tamil
    -0.37
    oredCriteria
    -0.36
     Collin
    -0.36
     localObject
    -0.36
     С
    -0.35
     sprout
    -0.35
    置
    -0.35
    POSITIVE LOGITS
     highway
    1.31
     Highway
    1.28
    highway
    1.26
     HIGHWAY
    1.23
    Highway
    1.22
     highways
    1.09
     Hwy
    1.05
     Highways
    0.92
     carretera
    0.85
     ſche
    0.83
    Activations Density 0.007%

    No Known Activations