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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27995
    Prev
    Next
    INDEX
    Explanations

    the beginning of paragraphs or sections in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.64
    IContainer
    -0.58
    JspWriter
    -0.57
     ModelExpression
    -0.56
    WireFormatLite
    -0.56
     CallOverrides
    -0.53
    RefNanny
    -0.52
     كومونز
    -0.51
     noqa
    -0.51
    WebControls
    -0.50
    POSITIVE LOGITS
    出版年
    0.67
    yadh
    0.55
     &___
    0.52
    mappedBy
    0.50
     inoxidable
    0.50
    ponses
    0.49
    ịch
    0.49
     tromper
    0.49
    sidemargin
    0.46
    ElementException
    0.45
    Activations Density 0.242%

    No Known Activations