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. 20-GEMMASCOPE-RES-16K
    6. 10101
    Prev
    Next
    INDEX
    Explanations

    instances of method declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.63
    Tikang
    -0.52
     fairness
    -0.49
     fair
    -0.49
     côtes
    -0.49
    uxley
    -0.47
    Heads
    -0.45
    cera
    -0.44
    ільки
    -0.43
    MENAFN
    -0.43
    POSITIVE LOGITS
     override
    1.15
    GEBURTSDATUM
    1.09
    override
    1.03
    Override
    1.02
    @
    0.75
     Overrides
    0.74
     Override
    0.72
    inheritDoc
    0.69
     overrides
    0.68
    ISupport
    0.68
    Activations Density 0.036%

    No Known Activations