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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 15937
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references within a regulatory or legislative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.62
    OrWhiteSpace
    -0.51
    inkin
    -0.50
     muualla
    -0.49
     المعيارى
    -0.49
    ValueStyle
    -0.46
    NewGuid
    -0.46
    värr
    -0.45
    ConfigureAwait
    -0.45
    螂
    -0.45
    POSITIVE LOGITS
    {§
    0.67
    Datuak
    0.67
    }")
    
    0.66
    Népesség
    0.60
    UnsafeEnabled
    0.59
     propOrder
    0.59
     transfieras
    0.59
     باخ
    0.58
    $.
    
    0.56
    toarele
    0.56
    Activations Density 1.008%

    No Known Activations