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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10898
    Prev
    Next
    INDEX
    Explanations

    unique attributes and craftsmanship of products

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

    associated with randomness or uniqueness

    np_acts-logits-general · gemini-2.0-flash

    random, unique, and unpredictable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     المعيارى
    -0.72
     intptr
    -0.71
    RenderAtEndOf
    -0.69
    AddTagHelper
    -0.67
     autorytatywna
    -0.66
     resourceCulture
    -0.64
    HtmlAttribute
    -0.63
    WithIOException
    -0.63
     initComponents
    -0.62
    RuleContext
    -0.60
    POSITIVE LOGITS
     unpredictable
    0.44
     random
    0.42
     randomly
    0.41
     variability
    0.36
    random
    0.35
    随机
    0.35
    ToTensor
    0.34
    ラン
    0.34
     подви
    0.34
     variable
    0.33
    Activations Density 0.392%

    No Known Activations