© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 115139
    Prev
    Next
    INDEX
    Explanations

    terms related to scanning and scan methodology

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

    scan time

    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
    ides
    -0.46
    dorf
    -0.45
    1
    -0.42
    getMinutes
    -0.41
     Fru
    -0.40
    lef
    -0.40
     Muth
    -0.40
     IV
    -0.40
     DIR
    -0.39
    
    -0.39
    POSITIVE LOGITS
     scan
    1.26
     SCAN
    1.23
     Scan
    1.20
    Scan
    1.18
    scan
    1.16
    SCAN
    1.14
     scanning
    1.09
    Scanning
    1.08
     Scanning
    1.06
     scans
    1.02
    Activations Density 0.009%

    No Known Activations