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. 5519
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to computing platforms and their characteristics

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

    platform / platforms

    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
     '\\;'
    -0.75
    parsedMessage
    -0.68
    AndEndTag
    -0.67
    withIdentifier
    -0.65
    MLLoader
    -0.65
     fotografico
    -0.63
    Hochspringen
    -0.60
    FieldBuilder
    -0.59
     InputDecoration
    -0.59
     EconPapers
    -0.59
    POSITIVE LOGITS
    Platform
    0.71
    platform
    0.65
     Platform
    0.60
     platform
    0.58
     platforms
    0.52
     differences
    0.52
    PLATFORM
    0.52
    Nationalité
    0.49
    platforms
    0.48
     PLATFORM
    0.47
    Activations Density 0.010%

    No Known Activations