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. 12-GEMMASCOPE-RES-65K
    6. 36686
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or paragraphs in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Aiheesta
    -0.61
     Egli
    -0.56
     theirs
    -0.56
    +#+
    -0.55
    BoxShadow
    -0.54
    CGRectMake
    -0.54
    出版年
    -0.52
     CHAPITRE
    -0.50
    Продам
    -0.50
     createContext
    -0.50
    POSITIVE LOGITS
    hilt
    0.59
    >>()
    0.56
    iredo
    0.55
    cshtml
    0.53
    ⓧ
    0.52
     Мексичка
    0.51
    发表于
    0.51
     commerciales
    0.50
    addCriterion
    0.49
     paix
    0.49
    Activations Density 0.007%

    No Known Activations