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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 8287
    Prev
    Next
    INDEX
    Explanations

    integrated discussions about safety and public policy related to technological implementations

    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
     complexes
    -0.86
     cheeses
    -0.86
     currencies
    -0.85
     buses
    -0.85
     viruses
    -0.84
     tumours
    -0.83
     medals
    -0.83
     dialects
    -0.83
     sauces
    -0.82
     niches
    -0.82
    POSITIVE LOGITS
     lèvres
    0.59
     autorités
    0.53
     épaules
    0.52
     bienfaits
    0.49
     modalités
    0.49
     bénéfices
    0.48
     vœux
    0.48
     prochaines
    0.47
     attentes
    0.45
     investissements
    0.44
    Activations Density 23.818%

    No Known Activations