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. 22-GEMMASCOPE-RES-16K
    6. 10519
    Prev
    Next
    INDEX
    Explanations

    specific programming or software-related content

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

    Code or identifiers followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    programming identifiers and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.73
    routeProvider
    -0.63
    qrstuvwxyz
    -0.63
    EDEFAULT
    -0.62
    外部リンク
    -0.61
     prêtres
    -0.60
     صوتيه
    -0.59
     épais
    -0.58
     sauvages
    -0.58
    ichio
    -0.57
    POSITIVE LOGITS
     initComponents
    0.59
     kasarigan
    0.59
     CreateTagHelper
    0.57
    complexContent
    0.54
    mtrl
    0.47
    scriptcase
    0.47
     للاسماء
    0.47
    ="@+
    0.46
    בור
    0.44
    WriteTagHelper
    0.44
    Activations Density 0.042%

    No Known Activations