© 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. 4543
    Prev
    Next
    INDEX
    Explanations

    variations and repetitions of the word "kind."

    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
    Autoritní
    -0.84
     Roskov
    -0.71
    Portale
    -0.62
    ScopeManager
    -0.56
    QtWidgets
    -0.55
     Baillargeon
    -0.55
    IsContent
    -0.55
    Ӏ
    -0.55
    ViewFeatures
    -0.54
    :✨
    -0.53
    POSITIVE LOGITS
    hearted
    0.79
    ling
    0.75
     hearted
    0.73
    gom
    0.70
    heartedly
    0.67
     soul
    0.62
    ERG
    0.60
    LING
    0.56
    les
    0.56
    lier
    0.55
    Activations Density 0.086%

    No Known Activations