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. 16-GEMMASCOPE-RES-16K
    6. 8920
    Prev
    Next
    INDEX
    Explanations

    LaTeX package commands and their configurations

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

    "usepackage" or LaTeX packages

    np_acts-logits-general · gemini-2.0-flash

    LaTeX \usepackage and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -1.06
    LookAnd
    -0.77
     oprot
    -0.76
     Autorisations
    -0.72
    IANGLES
    -0.71
    principalColumn
    -0.71
     NSCoder
    -0.71
    AndEndTag
    -0.70
    Salta
    -0.70
     OFDb
    -0.68
    POSITIVE LOGITS
    usepackage
    2.63
     Vex
    0.59
    Vex
    0.59
     économies
    0.57
    utus
    0.57
    <tr>
    0.56
     ECC
    0.55
    package
    0.55
    Spice
    0.55
    $\\
    0.55
    Activations Density 0.017%

    No Known Activations