© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13452
    Prev
    Next
    INDEX
    Explanations

    information related to potential benefits or advantages in various contexts, particularly in medical and environmental discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens before "benefit"

    np_acts-logits-general · gemini-2.0-flash

    might benefit or gain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fallu
    -0.47
    र्व
    -0.47
    Източници
    -0.47
    لمانيا
    -0.47
    pakking
    -0.46
    quiera
    -0.46
    ükemmel
    -0.45
    ero
    -0.45
    angk
    -0.44
     faudra
    -0.43
    POSITIVE LOGITS
     benefit
    2.81
     benefited
    2.61
    benefit
    2.53
     benefitted
    2.45
    Benefit
    2.43
     Benefit
    2.41
     benefiting
    2.36
     benefits
    2.22
     BENE
    2.17
    benefits
    1.97
    Activations Density 0.293%

    No Known Activations