© 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. 8958
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental and legal frameworks, particularly involving human and animal health contexts

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

    Relates a species to an organ or disease

    np_acts-logits-general · gemini-2.0-flash

    human, bovine, cellular structures

    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
     Inscrivez
    -0.48
     auroit
    -0.46
     betweenstory
    -0.44
     agujas
    -0.42
     recuer
    -0.42
     répon
    -0.42
     orígenes
    -0.42
     caminos
    -0.42
     debajo
    -0.41
    ึ้น
    -0.40
    POSITIVE LOGITS
     dietary
    0.64
    acterial
    0.62
    })->
    0.61
     audi
    0.60
     Indian
    0.59
     neurop
    0.59
    robial
    0.59
    rainian
    0.59
    bial
    0.59
    ")));
    0.57
    Activations Density 0.654%

    No Known Activations