© 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. 7-GEMMASCOPE-RES-16K
    11. 6516
    Prev
    Next
    INDEX
    Explanations

    words related to selection and choice-making

    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
    Pratique
    -0.71
    adaptiveStyles
    -0.68
    liminaries
    -0.68
    ocumented
    -0.66
     nyata
    -0.66
     فريبيس
    -0.64
    documented
    -0.64
     /\.(
    -0.64
    ViewFeatures
    -0.64
    hende
    -0.63
    POSITIVE LOGITS
     selects
    1.67
     chosen
    1.63
     choose
    1.58
     choosing
    1.58
    choose
    1.56
     selecting
    1.54
     Choose
    1.54
     selection
    1.53
     Choosing
    1.51
     Selecting
    1.51
    Activations Density 0.336%

    No Known Activations