Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 10160
    Prev
    Next
    INDEX
    Explanations

    mentions of the user or their ownership in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.97
    AddTagHelper
    -0.88
    SBATCH
    -0.88
    PreferredItem
    -0.87
    IntoConstraints
    -0.86
    WebServlet
    -0.85
    kháu
    -0.84
    tvguidetime
    -0.83
    TemporalType
    -0.83
    AsUp
    -0.83
    POSITIVE LOGITS
     your
    0.58
     cref
    0.45
     nhiên
    0.44
    Each
    0.43
     désign
    0.43
     chaque
    0.43
    ctible
    0.43
     needs
    0.43
     each
    0.42
     lisäksi
    0.42
    Activations Density 0.096%

    No Known Activations