© 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. 11981
    Prev
    Next
    INDEX
    Explanations

    elements related to strategy identification and evaluation in healthcare contexts

    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
    multline
    -0.58
    iastical
    -0.56
    wpi
    -0.55
    rungsseite
    -0.55
     Meksiku
    -0.54
    AllowAnonymous
    -0.52
     Италијани
    -0.52
    scalatest
    -0.51
    íncipe
    -0.51
    했습니다
    -0.51
    POSITIVE LOGITS
     areas
    1.47
    areas
    1.25
    Areas
    1.24
     weaknesses
    1.23
     Areas
    1.23
     gaps
    1.05
     AREAS
    1.05
     weakness
    1.02
     strengths
    1.01
     weak
    1.00
    Activations Density 0.369%

    No Known Activations