© 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. 5-GEMMASCOPE-RES-16K
    11. 6907
    Prev
    Next
    INDEX
    Explanations

    instances of user interface elements and actions related to a grading system or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.78
     AssemblyVersion
    -0.71
    rinfo
    -0.66
     Réponses
    -0.65
     onPostExecute
    -0.62
     IERC
    -0.61
    ंदीखरीदारी
    -0.60
    ArgsConstructor
    -0.60
     radiators
    -0.59
     BSEB
    -0.57
    POSITIVE LOGITS
    RegressionTest
    0.50
     god
    0.48
     @
    0.48
     un
    0.47
     Fil
    0.46
     und
    0.46
    olution
    0.44
     an
    0.43
    UrlResolution
    0.43
     God
    0.43
    Activations Density 0.253%

    No Known Activations