© 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. 8836
    Prev
    Next
    INDEX
    Explanations

    probability-related queries and calculations

    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
     Lupin
    -0.56
     Kaufman
    -0.56
    AndEndTag
    -0.53
     Glaser
    -0.52
     Herzog
    -0.50
     Bader
    -0.49
     McFarland
    -0.47
     Burton
    -0.47
     Murphy
    -0.46
     Nagel
    -0.46
    POSITIVE LOGITS
     CCC
    1.42
     PP
    1.35
     BBB
    1.34
     SSS
    1.34
     JJ
    1.34
     BB
    1.33
     PPP
    1.31
     GG
    1.29
     RR
    1.27
     TT
    1.25
    Activations Density 6.884%

    No Known Activations