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. 9-GEMMASCOPE-RES-131K
    6. 23912
    Prev
    Next
    INDEX
    Explanations

    the concept of "main" or "primary" focus or element in a text

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

    main followed by a role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToBounds
    -0.55
    Rüyada
    -0.50
    Попис
    -0.47
     AssemblyCulture
    -0.47
    fromnode
    -0.46
     ब्रेकडाउन
    -0.45
     հղումներ
    -0.44
     kaarangay
    -0.43
    MessageTagHelper
    -0.40
    Bronnen
    -0.40
    POSITIVE LOGITS
    Primary
    0.47
     primary
    0.47
    NameInMap
    0.47
    primary
    0.45
     PRIMARY
    0.44
     pleaſure
    0.44
     Primary
    0.43
    ſelf
    0.41
    OGND
    0.40
    moil
    0.40
    Activations Density 0.044%

    No Known Activations