© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 674
    Prev
    Next
    INDEX
    Explanations

    terms related to biotechnology and genetic research

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

    followed by scientific terms or explanations

    np_acts-logits-general · gemini-2.0-flash

    research and discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.37
     shall
    -0.35
    <bos>
    -0.34
     disponer
    -0.33
     m
    -0.33
    /
    -0.32
    oader
    -0.32
    ↵
    -0.32
      
    -0.31
    ↵↵
    -0.31
    POSITIVE LOGITS
     ſch
    0.71
     feroit
    0.71
     invokingState
    0.68
     ſche
    0.67
     ſeinen
    0.66
     juſ
    0.66
     Houſe
    0.66
     disambiguazione
    0.65
     ſever
    0.64
     Reſ
    0.64
    Activations Density 0.417%

    No Known Activations