© 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. 1888
    Prev
    Next
    INDEX
    Explanations

    numerical data and relevant assessments in the context of medical trials or evaluations

    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
     purpoſe
    -0.80
    MessageTagHelper
    -0.75
     Majefty
    -0.71
     greateſt
    -0.69
     Partagez
    -0.68
    RegressionTest
    -0.66
     ſche
    -0.66
     ſch
    -0.65
     beſt
    -0.64
     Viceroy
    -0.64
    POSITIVE LOGITS
     later
    0.69
     in
    0.59
     others
    0.59
    -------
    0.59
     intptr
    0.56
    elos
    0.52
    StoryboardSegue
    0.52
     on
    0.51
     di
    0.51
    AutoField
    0.51
    Activations Density 0.503%

    No Known Activations