© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1822
    Prev
    Next
    INDEX
    Explanations

    demographic information related to individuals and incidents involving law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    -0.71
     Majefty
    -0.70
     Horacio
    -0.67
     espagne
    -0.64
    المشاركات
    -0.64
     Anſ
    -0.63
    ſelves
    -0.61
     Conſ
    -0.60
     pleaſure
    -0.60
     purpoſe
    -0.58
    POSITIVE LOGITS
    /**
    0.58
    NUMX
    0.57
     <=",
    0.57
    JpaRepository
    0.56
     >=",
    0.52
     createContext
    0.47
     sī
    0.47
    setCellValue
    0.45
    äsident
    0.45
     entre
    0.44
    Activations Density 1.362%

    No Known Activations