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. 23-GEMMASCOPE-RES-131K
    6. 23137
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions associated with programming and data structures

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trend
    -0.38
    상
    -0.38
    MessageState
    -0.36
     상
    -0.33
    strains
    -0.33
     vernie
    -0.33
     camisetas
    -0.32
     recombination
    -0.31
     Manif
    -0.31
    }();
    -0.31
    POSITIVE LOGITS
    tagHelperRunner
    0.74
    verwijspagina
    0.57
    istoitu
    0.53
     contributo
    0.51
    astéroïdes
    0.50
     старости
    0.49
     ListTile
    0.48
    ähteet
    0.47
    ListTile
    0.46
     Komunikasi
    0.46
    Activations Density 0.114%

    No Known Activations