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. 692
    Prev
    Next
    INDEX
    Explanations

    formatting and structural elements within a scientific document

    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
    yntaxException
    -0.63
    Hozzáférés
    -0.58
    oa̍t
    -0.55
     通販
    -0.53
    Rujuakan
    -0.52
    (&:
    -0.52
     Erişim
    -0.52
    SOUNDBITE
    -0.50
    tillinger
    -0.50
    ագրություններ
    -0.49
    POSITIVE LOGITS
     GoogleFonts
    0.63
    astify
    0.63
     Normdatei
    0.61
    UnknownFieldSet
    0.54
     Footnote
    0.53
     footnote
    0.53
     مرئيه
    0.52
     UserRepository
    0.51
    footnote
    0.50
    fromnode
    0.50
    Activations Density 0.344%

    No Known Activations