© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 710
    Prev
    Next
    INDEX
    Explanations

    mentions of specific items or tasks related to projects and their completion

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

    per/each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ویکی‌پدی
    -0.52
     Мексичка
    -0.52
     <<<<<<<<<<<<<<
    -0.51
    
    -0.49
    SBATCH
    -0.48
     تضيفلها
    -0.47
    invokeLater
    -0.46
    Skocz
    -0.45
    GIVEREF
    -0.44
    toThrow
    -0.44
    POSITIVE LOGITS
     apiece
    0.45
     annually
    0.45
     EACH
    0.41
     each
    0.38
    onSave
    0.37
     cumulative
    0.37
     CP
    0.37
     per
    0.36
    ImageField
    0.35
     averaging
    0.35
    Activations Density 0.082%

    No Known Activations