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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 13298
    Prev
    Next
    INDEX
    Explanations

    terms related to legal validity and contract status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kloped
    -0.93
     Réponses
    -0.81
    Tikang
    -0.75
     pinulongan
    -0.73
    TypedDataSet
    -0.68
     Roskov
    -0.67
    EndContext
    -0.63
    ArrowToggle
    -0.62
    fjspx
    -0.62
     رش
    -0.57
    POSITIVE LOGITS
     gül
    0.83
     expires
    0.82
     expired
    0.82
     expiring
    0.78
     validity
    0.78
     válido
    0.76
     valide
    0.75
     valid
    0.75
     geldig
    0.75
     expire
    0.74
    Activations Density 0.518%

    No Known Activations