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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6876
    Prev
    Next
    INDEX
    Explanations

    instances of image or figure references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.76
    pulumi
    -0.72
     propOrder
    -0.71
    OGND
    -0.68
    localVar
    -0.65
    fillType
    -0.63
    oredCriteria
    -0.62
    ThroughAttribute
    -0.62
    tagHelper
    -0.61
    NameInMap
    -0.61
    POSITIVE LOGITS
    fortawesome
    0.73
    TagMode
    0.68
     بعدی
    0.61
     parlant
    0.56
     ibid
    0.55
    kjø
    0.54
     rağmen
    0.53
    ydı
    0.52
     dépos
    0.51
     Osorio
    0.50
    Activations Density 0.036%

    No Known Activations