© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4208
    Prev
    Next
    INDEX
    Explanations

    words indicating relationships and actions in contexts of dependency or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >>();
    -0.55
    rinas
    -0.53
     ter
    -0.53
    WithEmail
    -0.51
    省市镇
    -0.50
     Kid
    -0.48
     also
    -0.47
     Cla
    -0.47
     Dra
    -0.47
    ')")
    -0.46
    POSITIVE LOGITS
    QMetaType
    0.81
     numberWith
    0.78
    +#+#
    0.77
    \{\\
    0.71
     Jurí
    0.69
     anún
    0.69
     okuyayım
    0.69
     Partagez
    0.67
    PickerController
    0.66
     désolés
    0.66
    Activations Density 0.584%

    No Known Activations