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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 945
    Prev
    Next
    INDEX
    Explanations

    financial metrics and details related to company performance

    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
    MigrationBuilder
    -0.60
     bezeichneter
    -0.59
     cherchés
    -0.58
    tdessen
    -0.56
    lwjgl
    -0.53
    Xna
    -0.53
    ]}"
    -0.51
    xaml
    -0.50
    ClCompile
    -0.50
    มาณ
    -0.49
    POSITIVE LOGITS
    截至
    1.03
    截止
    0.84
    ณ
    0.80
     at
    0.76
     Roskov
    0.72
    saat
    0.68
     Zeitpunkt
    0.64
    AtEndOf
    0.63
     momento
    0.62
    χρι
    0.61
    Activations Density 0.616%

    No Known Activations