Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2800
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific terms related to derivatives and their calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    Personendaten
    -0.97
     AssemblyCulture
    -0.66
    клопе
    -0.52
    multirow
    -0.52
    //
    -0.52
     Paglinawan
    -0.52
     незавершена
    -0.51
    classnames
    -0.50
    pushFollow
    -0.49
    ftagPool
    -0.49
    POSITIVE LOGITS
    4
    0.62
     cuarta
    0.60
     Fourth
    0.57
    Fourth
    0.56
     vierten
    0.54
     fourth
    0.54
     NgModule
    0.53
     typelib
    0.53
     AttributeSet
    0.53
    IsInitialized
    0.52
    Activations Density 0.791%

    No Known Activations