© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 4370
    Prev
    Next
    INDEX
    Explanations

    terms associated with radiation and its effects on cells and biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OnInit
    -0.63
     appartiennent
    -0.52
    帖最后由
    -0.51
    qrstuvwxyz
    -0.50
    bonucleic
    -0.50
    yaxis
    -0.50
    Saving
    -0.48
    eclipse
    -0.48
     Dan
    -0.48
    <0xB7>
    -0.48
    POSITIVE LOGITS
     effects
    0.80
     effect
    0.74
     influence
    0.71
     affect
    0.71
     Roskov
    0.69
    induced
    0.67
    Effects
    0.66
     invloed
    0.66
     affects
    0.64
    の影響
    0.63
    Activations Density 1.707%

    No Known Activations