Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 7019
    Prev
    Next
    INDEX
    Explanations

    numerical data and measurements related to scientific experiments and observations

    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
     SERIES
    -0.57
    Enllaces
    -0.56
     numerus
    -0.56
    Series
    -0.56
     Untitled
    -0.55
     Series
    -0.54
     typeof
    -0.53
     PEND
    -0.50
     series
    -0.50
     Pend
    -0.49
    POSITIVE LOGITS
    Демографія
    0.63
     keV
    0.62
     eV
    0.62
     viewType
    0.61
     MeV
    0.58
    eV
    0.58
    MeV
    0.57
     Jy
    0.57
    keV
    0.56
     GeV
    0.53
    Activations Density 1.407%

    No Known Activations