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. 2426
    Prev
    Next
    INDEX
    Explanations

    terms associated with confirmation codes and account management

    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
     nahilalakip
    -0.73
     متعلقه
    -0.64
     '\\;'
    -0.63
    RenderAtEndOf
    -0.62
    RectangleBorder
    -0.56
     للمعارف
    -0.53
    цездатний
    -0.52
     ModelExpression
    -0.52
    GEBURTSDATUM
    -0.50
    hnung
    -0.49
    POSITIVE LOGITS
     nélk
    0.80
     šķ
    0.78
     vandens
    0.78
     picioare
    0.76
     čier
    0.75
     vastaan
    0.74
     bēr
    0.74
     vė
    0.73
     aikaa
    0.73
     virš
    0.70
    Activations Density 0.135%

    No Known Activations