© 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. 15-GEMMASCOPE-RES-16K
    6. 3740
    Prev
    Next
    INDEX
    Explanations

    references to individuals and entities involved in specific contexts or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     обращения
    -0.51
     Polda
    -0.50
     Reverso
    -0.49
    mbda
    -0.48
     prestations
    -0.46
    Fitting
    -0.45
     spontan
    -0.45
     dilu
    -0.44
    monde
    -0.44
     Königreich
    -0.44
    POSITIVE LOGITS
     responsible
    0.75
     staff
    0.75
     personnel
    0.74
     administrative
    0.74
     bureaucratic
    0.73
     authority
    0.72
     managerial
    0.72
     bureaucracy
    0.71
    responsible
    0.71
    senior
    0.70
    Activations Density 0.363%

    No Known Activations