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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 984
    Prev
    Next
    INDEX
    Explanations

    structured data and elements in code

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

    code and data identifiers

    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
     arşivlendi
    -0.52
    astéroïdes
    -0.50
     <=",
    -0.49
    webElement
    -0.46
     оригіналу
    -0.46
    invokeLater
    -0.45
     копия
    -0.45
    writeFieldEnd
    -0.44
     protoimpl
    -0.44
    RefNanny
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.65
     betweenstory
    0.54
    protoimpl
    0.50
    ########.
    0.47
     Numerade
    0.46
    SBATCH
    0.40
    +#+
    0.40
    MemoryWarning
    0.36
    хьтан
    0.36
    Debian
    0.35
    Activations Density 0.097%

    No Known Activations