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. 1811
    Prev
    Next
    INDEX
    Explanations

    references to the concept of judgment or evaluation

    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
    Personensuche
    -0.76
     kasarigan
    -0.68
    homonymie
    -0.62
     cherchés
    -0.61
    expandindo
    -0.61
    
    -0.60
    SourceChecksum
    -0.57
     препратки
    -0.56
     utafitiHapana
    -0.56
    ScopeManager
    -0.55
    POSITIVE LOGITS
     lot
    0.73
    ](#
    0.54
     aéreas
    0.53
     certain
    0.52
    isier
    0.48
     trace
    0.48
     edelstahl
    0.46
     altro
    0.44
    ariConfig
    0.43
    rous
    0.43
    Activations Density 0.141%

    No Known Activations