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. 14248
    Prev
    Next
    INDEX
    Explanations

    phrases related to setting, achieving, and discussing goals and plans

    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
     PeEnEo
    -0.47
    TagMode
    -0.41
    sund
    -0.41
     dran
    -0.40
    providedIn
    -0.39
    madeus
    -0.38
     AW
    -0.38
    */),
    -0.38
     EW
    -0.37
    devServer
    -0.37
    POSITIVE LOGITS
     goals
    1.17
     objectives
    1.10
    Goals
    1.03
     goal
    1.02
    goals
    0.97
     Goals
    0.96
     Objectives
    0.93
    Goal
    0.93
    goal
    0.92
     Goal
    0.91
    Activations Density 0.288%

    No Known Activations