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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14412
    Prev
    Next
    INDEX
    Explanations

    technical terms and relationships regarding statistical analysis and regression models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exec
    -0.40
    ArgsConstructor
    -0.36
    NameInMap
    -0.35
    Executives
    -0.35
     Gor
    -0.35
     Exec
    -0.35
     FormData
    -0.34
     Raz
    -0.33
     Tis
    -0.33
    exec
    -0.32
    POSITIVE LOGITS
    目标
    0.54
    arakhand
    0.51
    IVEREF
    0.51
     purpoſe
    0.51
    的目标
    0.50
     Ziele
    0.50
    的目的
    0.50
     objetivo
    0.49
    目標
    0.49
     cible
    0.49
    Activations Density 1.170%

    No Known Activations