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. 1002
    Prev
    Next
    INDEX
    Explanations

    references to historical events and ancient populations

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

    Noe or Hamlets

    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
    èves
    -0.48
    umblebee
    -0.47
    lardır
    -0.46
    SequentialGroup
    -0.43
    ğmen
    -0.43
    wires
    -0.43
    ضايا
    -0.42
     Vamp
    -0.42
    tadır
    -0.42
     Butterflies
    -0.42
    POSITIVE LOGITS
     Noah
    0.57
     onAnimation
    0.53
    Noah
    0.51
     BIBSYS
    0.48
    ViewImports
    0.47
     BoxDecoration
    0.46
     boat
    0.46
    脚注の使い方
    0.43
    TagMode
    0.43
    providedIn
    0.43
    Activations Density 0.002%

    No Known Activations