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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 68620
    Prev
    Next
    INDEX
    Explanations

    references to the act of consideration and evaluation in scientific contexts

    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
    flashdata
    -0.49
    Itoa
    -0.33
    addContainerGap
    -0.28
    IonicModule
    -0.28
     Spitze
    -0.27
    apimachinery
    -0.27
    IBAction
    -0.27
     Meksiku
    -0.26
     -¿
    -0.25
     zuen
    -0.25
    POSITIVE LOGITS
     betweenstory
    0.64
    出版年
    0.61
    migrationBuilder
    0.58
     المعيارى
    0.54
     propositions
    0.53
    Données
    0.52
     createState
    0.52
     Vessel
    0.52
    aluc
    0.52
     CURIAM
    0.51
    Activations Density 0.164%

    No Known Activations