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. 21-GEMMASCOPE-RES-16K
    6. 12842
    Prev
    Next
    INDEX
    Explanations

    terms related to health risks and diseases affecting humans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.59
     saites
    -0.53
     समीक्षाओं
    -0.48
     везе
    -0.47
    rency
    -0.47
     विश्वसनीयता
    -0.47
    LIOT
    -0.46
    ytä
    -0.45
     wireType
    -0.43
     }}"></
    -0.43
    POSITIVE LOGITS
     human
    3.32
     humans
    3.02
    human
    2.91
    Human
    2.67
     HUMAN
    2.58
     Human
    2.58
     humain
    2.53
     Humans
    2.50
     humano
    2.50
    Humans
    2.49
    Activations Density 0.476%

    No Known Activations