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. 2608
    Prev
    Next
    INDEX
    Explanations

    instances of generic programming terms or classes

    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
    entend
    -0.49
     radiador
    -0.47
     entsch
    -0.46
    twimg
    -0.45
    ENCODE
    -0.45
     todella
    -0.45
    charCodeAt
    -0.45
    loyd
    -0.44
    tifikat
    -0.44
     budaya
    -0.44
    POSITIVE LOGITS
    Generic
    2.85
     Generic
    2.07
    generic
    1.92
     generic
    1.82
    GENERIC
    1.52
    Tikang
    1.10
     gener
    1.04
     متعلقه
    1.00
    generics
    0.93
     EconPapers
    0.92
    Activations Density 0.019%

    No Known Activations