Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3753
    Prev
    Next
    INDEX
    Explanations

    references to inaccuracies or errors in responses

    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
     Révolution
    -0.57
     Heron
    -0.54
     heron
    -0.53
     casquette
    -0.52
     Keenan
    -0.47
     Dian
    -0.46
     boisson
    -0.46
     poitrine
    -0.46
    OutputPath
    -0.45
     Cochran
    -0.45
    POSITIVE LOGITS
     Bane
    0.83
     Dine
    0.82
    DCE
    0.82
    bane
    0.81
     Cline
    0.81
     Vane
    0.80
     Dane
    0.80
     Tate
    0.79
     Bate
    0.79
    MCE
    0.79
    Activations Density 2.596%

    No Known Activations