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. 69315
    Prev
    Next
    INDEX
    Explanations

    phrases related to nominations and achievements in the entertainment industry

    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
    basedir
    -0.35
     Wurzel
    -0.35
     ourselves
    -0.34
     ...
    -0.33
     ușor
    -0.33
     schließen
    -0.32
    MeasureSpec
    -0.31
     Schmer
    -0.31
     habido
    -0.31
     Pardo
    -0.31
    POSITIVE LOGITS
     CreateTagHelper
    0.81
    tagHelperRunner
    0.70
    +#+
    0.68
     незавершена
    0.68
    CppMethod
    0.64
    RenderAtEndOf
    0.63
     yyb
    0.60
    󠁿
    0.59
    IsContent
    0.59
     Geſch
    0.59
    Activations Density 0.084%

    No Known Activations