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. 16-GEMMASCOPE-RES-16K
    6. 12865
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers following citations or data

    np_acts-logits-general · gemini-2.0-flash

    legal citations with S.Ct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    envoy
    -0.55
     tromper
    -0.53
    ardless
    -0.51
    щество
    -0.49
     Bür
    -0.48
    netje
    -0.48
     poil
    -0.47
     lunak
    -0.47
     personnelle
    -0.47
    offee
    -0.47
    POSITIVE LOGITS
     Paglinawan
    0.87
    protoimpl
    0.87
    клопе
    0.85
    存于互联网档案馆
    0.83
    AccessorTable
    0.80
    TagMode
    0.73
    dataclass
    0.71
    oa̍t
    0.69
     дописавши
    0.68
     noqa
    0.67
    Activations Density 0.795%

    No Known Activations