© 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. 24-GEMMASCOPE-RES-16K
    11. 13847
    Prev
    Next
    INDEX
    Explanations

    terms related to pets, specifically dogs and their owners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "ter", "tico", "rone", "ri", or "pen"

    np_acts-logits-general · gemini-2.0-flash

    pet and dog

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.89
    \{\\
    -0.71
     مشين
    -0.61
    expandindo
    -0.59
    enumi
    -0.57
     للمعارف
    -0.57
    RenderAtEndOf
    -0.56
    StoryboardSegue
    -0.54
    Искәрмәләр
    -0.53
    homonymie
    -0.52
    POSITIVE LOGITS
     lover
    0.57
    InteropServices
    0.56
     lovers
    0.55
     useRef
    0.54
     sumpay
    0.52
    ConfigureAwait
    0.52
     thước
    0.51
    MENAFN
    0.51
    Vidi
    0.50
    منت
    0.48
    Activations Density 0.191%

    No Known Activations