© 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. 25-GEMMASCOPE-RES-16K
    11. 3738
    Prev
    Next
    INDEX
    Explanations

    specific terms related to medical studies and visual acuity assessments

    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
     Ruth
    -1.00
    Ruth
    -0.93
     Ir
    -0.89
     Harper
    -0.86
     Irving
    -0.84
     Dave
    -0.83
     RUTH
    -0.80
    Ir
    -0.78
     Roth
    -0.78
     ir
    -0.76
    POSITIVE LOGITS
     Craven
    0.84
     Kamen
    0.73
     Parker
    0.72
     Fila
    0.69
     Huse
    0.68
     Picchu
    0.65
     Tup
    0.65
     Montagu
    0.64
     Aurora
    0.64
     Enfield
    0.63
    Activations Density 1.423%

    No Known Activations