© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4791
    Prev
    Next
    INDEX
    Explanations

    mathematical vocabulary related to derivatives and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ūrė
    -0.50
    lė
    -0.47
    +#+
    -0.47
    nof
    -0.46
    εια
    -0.44
     tartalomajánló
    -0.44
     ít
    -0.43
    ття
    -0.43
    albeit
    -0.42
     maturing
    -0.42
    POSITIVE LOGITS
    $_['
    0.90
    djangoproject
    0.86
    <?
    0.81
    findpost
    0.79
    RegressionTest
    0.75
     disponibilités
    0.69
     Drapeau
    0.67
    dataclass
    0.66
    awtextra
    0.64
     vulgaires
    0.64
    Activations Density 0.807%

    No Known Activations