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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13254
    Prev
    Next
    INDEX
    Explanations

    references to people, particularly with titles like "Mr." and "Ms."

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ivelany
    -0.56
    地说道
    -0.51
     Lune
    -0.50
     [],
    
    -0.47
     aanbod
    -0.47
     :)</
    -0.47
    _();
    -0.46
     расте
    -0.45
    nter
    -0.45
    raiz
    -0.45
    POSITIVE LOGITS
    ⓧ
    0.71
     <=",
    0.67
    NameInMap
    0.61
     nahilalakip
    0.61
    ulemon
    0.61
    ivably
    0.61
    ///</
    0.60
     '{@
    0.59
    Rüyada
    0.58
    SourceChecksum
    0.58
    Activations Density 0.071%

    No Known Activations