© 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-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 703
    Prev
    Next
    INDEX
    Explanations

    email addresses and web domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    email addresses and domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.78
    IndentedString
    -0.72
    TagMode
    -0.71
     AssemblyCulture
    -0.70
    providedIn
    -0.69
    webElementXpaths
    -0.66
    RegressionTest
    -0.65
    UrlResolution
    -0.65
    adaptiveStyles
    -0.64
    новниш
    -0.63
    POSITIVE LOGITS
     before
    0.42
     beforehand
    0.39
     BEFORE
    0.36
     regarding
    0.36
     Kammer
    0.34
     prior
    0.34
     with
    0.33
     ext
    0.32
     subject
    0.30
     or
    0.30
    Activations Density 0.006%

    No Known Activations