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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 8110
    Prev
    Next
    INDEX
    Explanations

    words that denote exceptional quality or excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.99
     חיצוניים
    -0.82
    bcryptjs
    -0.67
     flesta
    -0.66
    EndGlobalSection
    -0.66
    ('/')
    -0.61
    dération
    -0.59
    pulumi
    -0.59
    resizingMask
    -0.58
    PHeader
    -0.57
    POSITIVE LOGITS
     exceptional
    1.24
     Exceptional
    1.05
    Exceptional
    1.03
     eccell
    0.94
     outstanding
    0.91
     exceptionnel
    0.89
    Exception
    0.87
     exceptionally
    0.83
    exception
    0.82
    Outstanding
    0.81
    Activations Density 0.111%

    No Known Activations