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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1735
    Prev
    Next
    INDEX
    Explanations

    prepositions and their frequency in describing relationships between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    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
    MLLoader
    -0.69
     HttpNotFound
    -0.67
     Оно
    -0.59
     Twe
    -0.58
     Hege
    -0.57
    GEBURTSDATUM
    -0.57
    SequentialGroup
    -0.56
    ærke
    -0.55
    ptest
    -0.54
     Betis
    -0.54
    POSITIVE LOGITS
     this
    0.84
    this
    0.75
     these
    0.57
     mukaan
    0.54
    klju
    0.53
     hierdie
    0.53
    putan
    0.50
    Acest
    0.50
    these
    0.49
     tohoto
    0.49
    Activations Density 0.336%

    No Known Activations