© 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. 4-GEMMASCOPE-RES-16K
    11. 3671
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of "matter" or importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    guisement
    -0.56
     uovo
    -0.52
    >−
    -0.51
     sagesse
    -0.49
     ann
    -0.49
    riwal
    -0.48
     graisse
    -0.47
     propriété
    -0.47
    scm
    -0.47
     conseille
    -0.46
    POSITIVE LOGITS
     matter
    0.81
    NameInMap
    0.78
    rawDesc
    0.74
     transfieras
    0.73
     invokingState
    0.72
    DrawerToggle
    0.68
    Географи
    0.67
     cuestión
    0.67
    queryInterface
    0.66
     questão
    0.66
    Activations Density 0.172%

    No Known Activations