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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39123
    Prev
    Next
    INDEX
    Explanations

    terms and references related to medical conditions, treatments, and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.81
     linkovi
    -0.67
    rrggbb
    -0.63
    Autoritní
    -0.61
    WithIOException
    -0.59
    сторія
    -0.59
    __":
    
    -0.58
    ativement
    -0.58
     незавершена
    -0.57
    urally
    -0.55
    POSITIVE LOGITS
    ysy
    0.57
     ventes
    0.54
    omitempty
    0.51
    AutoScaleMode
    0.50
     '</
    0.49
    ->__
    0.46
     гу
    0.46
    ítő
    0.46
     professionali
    0.46
    Vaya
    0.45
    Activations Density 0.237%

    No Known Activations