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. 24-GEMMASCOPE-RES-16K
    6. 4586
    Prev
    Next
    INDEX
    Explanations

    references to time durations and quantities

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

    Numbers or quantities

    np_acts-logits-general · gemini-2.0-flash

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.90
    OGND
    -0.69
    FieldDescriptor
    -0.67
    raszam
    -0.66
    SequentialGroup
    -0.64
    colgroup
    -0.64
     initComponents
    -0.62
    олові
    -0.62
     للمعارف
    -0.62
     بيها
    -0.62
    POSITIVE LOGITS
     twenty
    1.00
     fifty
    0.96
     thirty
    0.96
     forty
    0.95
     ninety
    0.94
     eighty
    0.92
     sixty
    0.90
     seventy
    0.90
     twelve
    0.89
     sixteen
    0.87
    Activations Density 0.650%

    No Known Activations