© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10091
    Prev
    Next
    INDEX
    Explanations

    terms related to experimental biology, particularly focusing on in vitro and in vivo studies

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

    "in vitro" followed by punctuation or tests

    np_acts-logits-general · gemini-2.0-flash

    in vitro tests and findings

    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
    utilisons
    -0.70
     Signalez
    -0.64
    Weblinks
    -0.60
     démission
    -0.59
     propriétaires
    -0.58
     puol
    -0.56
     jüng
    -0.54
     pères
    -0.52
    SourceChecksum
    -0.52
     kérdés
    -0.52
    POSITIVE LOGITS
     basis
    0.69
    $.
    0.66
    FDRE
    0.62
     approach
    0.61
     Shakspeare
    0.59
     Basis
    0.58
     counterparts
    0.56
     solutions
    0.56
    nehin
    0.56
    ++
    0.56
    Activations Density 0.592%

    No Known Activations