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. 12-GEMMASCOPE-RES-16K
    6. 5121
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating thresholds or limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.46
    hul
    -0.44
    mer
    -0.43
    zookeeper
    -0.42
     FormsModule
    -0.41
    erville
    -0.40
     बस
    -0.40
     counts
    -0.39
     CBS
    -0.39
    jointe
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.85
    GEBURTSDATUM
    0.82
     than
    0.82
     propOrder
    0.80
     >=",
    0.76
    ंदीखरीदारी
    0.76
    enumi
    0.74
    URLException
    0.73
     THAN
    0.72
     beyond
    0.70
    Activations Density 0.670%

    No Known Activations