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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14766
    Prev
    Next
    INDEX
    Explanations

    elements and structures in programming and markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.69
    OGND
    -0.68
    SourceChecksum
    -0.58
     oprot
    -0.57
    MessageOf
    -0.54
     intStringLen
    -0.52
    +#+#
    -0.48
    gitte
    -0.47
     fieldNum
    -0.47
    tagHelper
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.42
     crossorigin
    0.42
     ơn
    0.37
    綜合報導
    0.33
     Mérimée
    0.33
    ❋
    0.33
     prakty
    0.33
    대한
    0.32
    maketitle
    0.31
     fucking
    0.31
    Activations Density 14.832%

    No Known Activations