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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9548
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to durability and reliability of materials or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OnInit
    -0.63
    KommentareTeilen
    -0.59
    UnknownFieldSet
    -0.57
    databind
    -0.56
    XmlAccessType
    -0.55
    ukkig
    -0.54
    ViewInit
    -0.54
    ymce
    -0.54
    zepte
    -0.53
    KURZBESCHREIBUNG
    -0.52
    POSITIVE LOGITS
     wear
    1.02
     exposure
    0.91
     abuse
    0.85
     repeated
    0.85
     usage
    0.82
    Repeated
    0.79
     Repeated
    0.78
     overuse
    0.78
     Wear
    0.78
    Exposure
    0.77
    Activations Density 0.319%

    No Known Activations