© 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. 25-GEMMASCOPE-RES-16K
    11. 8142
    Prev
    Next
    INDEX
    Explanations

    information related to fashion and clothing retail, specifically targeting offers and services aimed at women looking for trendy styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MERCHANTABILITY
    -0.50
    Oof
    -0.50
    GEBURTS
    -0.50
     overheard
    -0.50
    ().__
    -0.46
    とはいえ
    -0.46
    outState
    -0.46
     regionally
    -0.45
    stdbool
    -0.45
     IRL
    -0.45
    POSITIVE LOGITS
     kindly
    0.87
     Kindly
    0.83
    Kindly
    0.78
     Regards
    0.75
    Whatsapp
    0.70
     visit
    0.70
     whatsapp
    0.70
    visit
    0.68
    Regards
    0.67
     Whatsapp
    0.66
    Activations Density 0.203%

    No Known Activations