© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14827
    Prev
    Next
    INDEX
    Explanations

    structured data or code elements, particularly in relation to key-value pairs and object-like syntax

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

    JSON ": { sequence

    np_acts-logits-general · gemini-2.0-flash

    boolean true

    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
    رشف
    -0.68
    varargin
    -0.65
     varargin
    -0.65
    !';
    -0.64
     ویکی‌آمباردا
    -0.63
     beginnetje
    -0.61
    ...');
    -0.58
     ویکی‌پدیای
    -0.57
     tartalomajánló
    -0.57
    Datuak
    -0.57
    POSITIVE LOGITS
     true
    1.24
    true
    1.22
     false
    0.99
    false
    0.99
     {
    0.92
     True
    0.91
    True
    0.90
    [-
    0.82
     [
    0.81
     -
    0.79
    Activations Density 0.629%

    No Known Activations