© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 937
    Prev
    Next
    INDEX
    Explanations

    code related to GUI components and their properties in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.70
    ImageContext
    -0.59
     MainAxisSize
    -0.58
    RTHOOK
    -0.56
    VersionUID
    -0.55
    UnsafeEnabled
    -0.55
    extAlignment
    -0.53
     pinulongan
    -0.53
     semelhantes
    -0.51
    ⓧ
    -0.51
    POSITIVE LOGITS
    colhead
    0.79
    StrictEqual
    0.55
     autorytatywna
    0.52
    toBeDefined
    0.51
    newblock
    0.50
     those
    0.50
    PositiveButton
    0.48
     rapporte
    0.46
    Scorecard
    0.45
    róleo
    0.45
    Activations Density 0.780%

    No Known Activations