© 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. 2815
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "one" and its equivalents in different languages

    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
     بيها
    -0.85
     متعلقه
    -0.75
     one
    -0.64
    EndContext
    -0.61
    jenige
    -0.59
     memoized
    -0.58
     albicans
    -0.58
     considérons
    -0.57
     stesso
    -0.56
     ones
    -0.56
    POSITIVE LOGITS
     autorytatywna
    0.82
     autre
    0.73
    certain
    0.66
     cuantos
    0.64
    maal
    0.61
     cuantas
    0.60
     quelconque
    0.60
    HomeAsUpEnabled
    0.59
     certaine
    0.59
    irme
    0.57
    Activations Density 0.036%

    No Known Activations