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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1000
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly in reference to data and measurements

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

    Numbers starting with 2, 4, 8, or 9 followed by a digit

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by punctuation or other numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    Personendaten
    -0.65
     للمعارف
    -0.63
    UnitTesting
    -0.62
     PeEnEo
    -0.61
     BoxFit
    -0.59
    +:+
    -0.58
     viſ
    -0.57
    الدراسه
    -0.57
    afficheront
    -0.56
    Tikang
    -0.56
    POSITIVE LOGITS
     falsas
    0.35
    mtrl
    0.35
     Constitucional
    0.33
    PathVariable
    0.31
     respirar
    0.30
    Atoi
    0.30
    bay
    0.29
     púrpura
    0.29
     Independencia
    0.28
    cyd
    0.28
    Activations Density 0.807%

    No Known Activations