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. 8083
    Prev
    Next
    INDEX
    Explanations

    expressions and terminology related to mathematical operations and scientific notation

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

    Mathematical expressions with underlines and "mkern" spacing

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbol precise spacing

    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
     autorytatywna
    -1.11
    SourceChecksum
    -0.97
    tagHelperRunner
    -0.97
     typelib
    -0.93
    GEBURTSDATUM
    -0.89
    InjectAttribute
    -0.89
    UnsafeEnabled
    -0.85
    Personensuche
    -0.85
    setVerticalGroup
    -0.80
     CreateTagHelper
    -0.79
    POSITIVE LOGITS
    ).
    
    0.78
    ...).
    0.75
    ).\\
    0.73
    .);
    0.71
    .).
    0.70
    .*/
    0.70
    …).
    0.67
     ).
    0.66
     –,
    0.65
    )。
    0.65
    Activations Density 5.669%

    No Known Activations