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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 440
    Prev
    Next
    INDEX
    Explanations

    technological terms and phrases related to programming or database queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to patents and technical specifications related to optical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    patent, diet, model, node

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -1.12
     Audiodateien
    -0.80
    LookAnd
    -0.79
    AsStream
    -0.79
    AndEndTag
    -0.78
    __(/*!
    -0.74
    forChild
    -0.73
     становника
    -0.71
    endpush
    -0.70
    DockStyle
    -0.69
    POSITIVE LOGITS
    دانشنامهٔ
    0.56
     المصرية
    0.47
    transQ
    0.46
     coal
    0.45
     vaccine
    0.45
     newspaper
    0.44
     jornal
    0.44
     armada
    0.44
    scriptcase
    0.43
     Uruguay
    0.43
    Activations Density 1.393%

    No Known Activations