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-2-2B
    4. Residual Stream - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28412
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or paragraphs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.54
    [toxicity=0]
    -0.48
    -0.47
    ↵
    -0.40
     
    -0.36
     [
    -0.36
    nisses
    -0.35
     (
    -0.35
    multirow
    -0.35
      
    -0.34
    POSITIVE LOGITS
    rungsseite
    0.88
    setVerticalGroup
    0.83
    دانشنامهٔ
    0.79
     дописавши
    0.78
    WebVitals
    0.76
    Hozzáférés
    0.75
    ")),
    0.73
    queryInterface
    0.73
    ])),
    0.73
    ))))))))
    0.71
    Activations Density 30.442%

    No Known Activations