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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80919
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to programming or computer operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.54
    providedIn
    -0.49
    reportWebVitals
    -0.48
    bootstrapcdn
    -0.47
    jsii
    -0.47
     rospy
    -0.45
    prepareStatement
    -0.44
    ContentValues
    -0.43
    Parcelize
    -0.43
     snippetHide
    -0.43
    POSITIVE LOGITS
    ExceptionHandler
    2.33
    ControllerAdvice
    0.74
    RequestMapping
    0.52
    aspectj
    0.52
    Reducers
    0.47
    ItemBackground
    0.46
    alarme
    0.45
     onCreateView
    0.44
     wireType
    0.44
    RequestHandler
    0.44
    Activations Density 0.000%

    No Known Activations