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. 1233
    Prev
    Next
    INDEX
    Explanations

    specific scientific terminology related to chemistry and biology

    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
     Anſ
    -0.56
    arXiv
    -0.52
    ConstraintMaker
    -0.52
    zufügen
    -0.50
     indisponible
    -0.50
    Enllaços
    -0.49
    брав
    -0.48
    <bos>
    -0.48
    baric
    -0.48
    paddingVertical
    -0.48
    POSITIVE LOGITS
    bbene
    0.65
    ToTensor
    0.65
     mergeFrom
    0.64
    tagHelperRunner
    0.64
    InstanceState
    0.60
    SharedDtor
    0.57
    UrlResolution
    0.57
    TypedDataSet
    0.57
     fermés
    0.55
     segreto
    0.53
    Activations Density 0.840%

    No Known Activations