© 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. 10562
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities or names related to locations or projects

    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
     Kura
    -0.63
     Merz
    -0.62
    ViewFeatures
    -0.56
     NCP
    -0.54
     Haf
    -0.53
    Kura
    -0.53
     kura
    -0.52
     SND
    -0.50
     ujednoznacz
    -0.50
     Mather
    -0.50
    POSITIVE LOGITS
     Ro
    2.92
    Ro
    2.76
     ro
    2.56
     RO
    2.53
    RO
    2.37
    ro
    2.05
     Ро
    1.88
     Roch
    1.73
     ROT
    1.71
    Ро
    1.71
    Activations Density 0.490%

    No Known Activations