© 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. 23-GEMMASCOPE-RES-16K
    11. 4655
    Prev
    Next
    INDEX
    Explanations

    situations involving danger or high stakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.77
    Tikang
    -0.71
    ThroughAttribute
    -0.67
    mybatisplus
    -0.66
    ArrowToggle
    -0.66
     disambiguazione
    -0.63
     المعيارى
    -0.63
    :✨
    -0.62
     betweenstory
    -0.61
    DllImport
    -0.61
    POSITIVE LOGITS
    ・
    0.57
    ──
    0.55
    ――
    0.55
    djangoproject
    0.53
    ㅋㅋ
    0.52
    shafen
    0.50
     pochette
    0.50
     『
    0.49
     subjug
    0.49
     troublesome
    0.48
    Activations Density 0.289%

    No Known Activations