© 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. 21-GEMMASCOPE-RES-16K
    6. 13327
    Prev
    Next
    INDEX
    Explanations

    mentions of outdoor activities and interests in lifestyle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    género
    -0.51
    ėjas
    -0.49
    RequiresApi
    -0.48
    LookAnd
    -0.48
     générations
    -0.48
    ibase
    -0.47
    TabStop
    -0.44
    InputBorder
    -0.44
    getSelection
    -0.44
    jspx
    -0.43
    POSITIVE LOGITS
     skiing
    1.58
     horseback
    1.54
     snowboarding
    1.48
     scuba
    1.45
     skateboarding
    1.40
     swimming
    1.40
     kayaking
    1.40
     golf
    1.35
     archery
    1.34
     Skiing
    1.33
    Activations Density 0.479%

    No Known Activations