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. 1-GEMMASCOPE-RES-16K
    6. 13801
    Prev
    Next
    INDEX
    Explanations

    numerical inputs and their structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    
    -0.55
    IUrlHelper
    -0.52
     estekak
    -0.50
     paik
    -0.47
     näm
    -0.47
    Soft
    -0.46
     engraçadas
    -0.45
     nõ
    -0.44
     OFDb
    -0.44
    //
    -0.43
    POSITIVE LOGITS
    <bos>
    0.86
    endphp
    0.79
    
    0.76
    setViewName
    0.76
     CGRectMake
    0.72
    tonode
    0.71
    itename
    0.70
    newArrayList
    0.68
     useCallback
    0.68
    Hozzáférés
    0.68
    Activations Density 0.409%

    No Known Activations