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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5730
    Prev
    Next
    INDEX
    Explanations

    terms that emphasize the utility and value of information

    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
    LookAnd
    -0.98
    dymyr
    -0.86
    OGND
    -0.83
     AspNetCore
    -0.76
     protoimpl
    -0.71
    cydow
    -0.69
    WebElementEntity
    -0.65
    addCriterion
    -0.65
    thenReturn
    -0.64
    Odkazy
    -0.63
    POSITIVE LOGITS
     useful
    1.73
    useful
    1.49
     Useful
    1.41
    Useful
    1.37
     helpful
    1.32
     valuable
    1.30
     útil
    1.27
     utile
    1.23
    valuable
    1.22
    Helpful
    1.17
    Activations Density 0.115%

    No Known Activations