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. 21-GEMMASCOPE-RES-16K
    6. 3049
    Prev
    Next
    INDEX
    Explanations

    terms that describe peculiarity or strangeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ztály
    -0.46
    @[+][
    -0.45
     referenties
    -0.45
    accharide
    -0.43
    essentiel
    -0.42
    createCanvas
    -0.42
     responsabile
    -0.41
    дию
    -0.41
    olars
    -0.41
    êque
    -0.40
    POSITIVE LOGITS
     étrange
    1.02
     strange
    1.01
     Strange
    1.01
    strange
    1.00
     odd
    0.98
     Weird
    0.96
    Strange
    0.95
    Weird
    0.94
     Unusual
    0.93
     coincidence
    0.92
    Activations Density 0.185%

    No Known Activations