© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27785
    Prev
    Next
    INDEX
    Explanations

    expressions of pleading or requesting

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

    begging for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherchés
    -0.92
     Мексичка
    -0.81
    VersionUID
    -0.80
    fromnode
    -0.78
     ExecuteAsync
    -0.76
     ***!
    -0.72
     BoxFit
    -0.70
     ICF
    -0.70
    liosis
    -0.69
    +#+#
    -0.67
    POSITIVE LOGITS
     auprès
    0.61
     ouvertes
    0.45
     professeurs
    0.43
     difficiles
    0.42
     Hard
    0.42
     către
    0.42
     begging
    0.41
     للبيع
    0.41
     for
    0.41
     soutenir
    0.41
    Activations Density 0.106%

    No Known Activations