Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 64702
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming-related terms and classes

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

    nextInt after Scanner

    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
    
    -0.44
    HomeAsUp
    -0.41
     LoginForm
    -0.35
    portál
    -0.35
    TRAILING
    -0.35
    qJ
    -0.35
     aix
    -0.35
    rungsseite
    -0.35
     she
    -0.35
     autorità
    -0.35
    POSITIVE LOGITS
     Scanner
    1.55
     scanner
    1.09
    Scanner
    1.05
    scanner
    0.89
     scanners
    0.86
     Scanning
    0.83
     scanning
    0.81
    canner
    0.80
     scan
    0.76
     scanned
    0.74
    Activations Density 0.000%

    No Known Activations