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. 10-GEMMASCOPE-RES-16K
    6. 10934
    Prev
    Next
    INDEX
    Explanations

    elements or aspects related to judgment or decisions in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithFormat
    -0.67
     V
    -0.66
    ManyToOne
    -0.65
    Hozzáférés
    -0.63
    nition
    -0.62
    âu
    -0.62
     parti
    -0.61
     Cat
    -0.60
     cre
    -0.60
    aurus
    -0.60
    POSITIVE LOGITS
    
    1.14
     
    1.13
    .
    1.06
    
    0.92
    IVEREF
    0.81
    #
    0.74
     pyrite
    0.73
     tranquillo
    0.72
     ordinaires
    0.69
     Pasha
    0.68
    Activations Density 0.080%

    No Known Activations