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. 20-GEMMASCOPE-RES-16K
    6. 12889
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     INSTITUTE
    -0.83
     Institute
    -0.83
     institute
    -0.82
     Instagram
    -0.81
     Islands
    -0.81
     islands
    -0.81
     infeksi
    -0.80
    Instagram
    -0.80
     Inst
    -0.79
    MatIconModule
    -0.79
    POSITIVE LOGITS
    esterno
    0.52
    aperto
    0.48
    Portale
    0.48
    Amérique
    0.47
     verdo
    0.46
    📘
    0.42
    basicConfig
    0.41
    outs
    0.41
    Outs
    0.41
    δου
    0.41
    Activations Density 0.324%

    No Known Activations