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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 5303
    Prev
    Next
    INDEX
    Explanations

    different modes or methods of communication

    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
     aspects
    -0.56
     période
    -0.56
     مواليد
    -0.52
    riterien
    -0.51
    aarrggbb
    -0.51
     período
    -0.50
     quantité
    -0.49
    ದು
    -0.49
     periodo
    -0.49
    aspects
    -0.48
    POSITIVE LOGITS
     operation
    0.92
     attack
    0.81
    operation
    0.80
     inquiry
    0.77
     enquiry
    0.76
     interaction
    0.73
     investigation
    0.70
     action
    0.68
     expression
    0.68
    OPERATION
    0.66
    Activations Density 0.577%

    No Known Activations