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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 14238
    Prev
    Next
    INDEX
    Explanations

    font styling and weight characteristics

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

    HTML/CSS related to font styling

    np_acts-logits-general · gemini-2.0-flash

    font weight or style

    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
     jsPsych
    -0.69
     kasarigan
    -0.60
    jspx
    -0.53
    BeginContext
    -0.51
    ycznie
    -0.49
     ansik
    -0.49
    bufio
    -0.49
     MSP
    -0.49
    ffilm
    -0.48
    ContentAlignment
    -0.47
    POSITIVE LOGITS
    bold
    0.90
     bold
    0.86
    Bold
    0.71
     FontWeight
    0.70
    BOLD
    0.69
     bolder
    0.68
     Bold
    0.68
    migrationBuilder
    0.62
     BOLD
    0.61
     <<<<<<<<<<<<<<
    0.60
    Activations Density 0.161%

    No Known Activations