© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 9448
    Prev
    Next
    INDEX
    Explanations

    assertions related to medical evaluations and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.66
    DoubleQuotes
    -0.59
    ########.
    -0.58
    opt
    -0.54
    ButterKnife
    -0.51
    oper
    -0.51
    objectId
    -0.50
    CloseOperation
    -0.48
    évaluateur
    -0.48
    operate
    -0.48
    POSITIVE LOGITS
     O
    3.48
    O
    2.87
     o
    1.72
     О
    1.65
    Ｏ
    1.47
    О
    1.36
     ओ
    1.21
     Ο
    1.14
     о
    1.13
    nO
    1.11
    Activations Density 0.959%

    No Known Activations