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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103058
    Prev
    Next
    INDEX
    Explanations

    SQL commands and structures related to updating and managing user search limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     esternos
    -0.55
     समीक्षाओं
    -0.54
    RTEE
    -0.54
    Carriera
    -0.49
     CreateTagHelper
    -0.49
     ModelExpression
    -0.48
    PCell
    -0.48
     ſmall
    -0.47
    abstractmethod
    -0.47
     initComponents
    -0.46
    POSITIVE LOGITS
     отредактировал
    0.40
    !(:
    0.38
    InjectAttribute
    0.37
     esercit
    0.36
    ↺
    0.35
    DockStyle
    0.35
     aniversário
    0.34
     blessé
    0.34
     damaged
    0.34
     change
    0.33
    Activations Density 0.005%

    No Known Activations