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. 57052
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software components and assembly attributes

    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
    )));
    
    -0.49
    >();
    
    -0.48
    vegas
    -0.47
    flashdata
    -0.45
    '])->
    -0.44
     memen
    -0.44
     sizeof
    -0.42
    sy
    -0.42
    ="{{
    -0.41
    [])
    
    -0.41
    POSITIVE LOGITS
     typelib
    0.83
    новништво
    0.76
     חיצוניים
    0.75
    ंदीखरीदारी
    0.73
    URLException
    0.70
     ModelExpression
    0.69
     ComVisible
    0.69
     defaultstate
    0.67
     resourceCulture
    0.67
    BufferException
    0.66
    Activations Density 0.004%

    No Known Activations