© 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. 15-GEMMASCOPE-RES-16K
    11. 3052
    Prev
    Next
    INDEX
    Explanations

    topics related to legal charges and the implications of agreements on criminal actions

    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
     pouvoirs
    -0.75
     skolen
    -0.74
     skolan
    -0.70
     négociations
    -0.68
     bénéfices
    -0.62
     Púb
    -0.61
     häl
    -0.61
     médicaux
    -0.60
     épaules
    -0.60
     tillgäng
    -0.59
    POSITIVE LOGITS
     themselves
    1.47
     their
    1.44
    their
    1.26
    Their
    1.24
    themselves
    1.23
     Their
    1.15
     respective
    1.04
     leurs
    0.99
     ihre
    0.97
    各自
    0.97
    Activations Density 1.591%

    No Known Activations