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. 2-GEMMASCOPE-RES-16K
    6. 8419
    Prev
    Next
    INDEX
    Explanations

    sections related to gene expression and associated experimental data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addGap
    -0.54
    бр
    -0.54
    もと
    -0.50
     Spisak
    -0.48
    ⎢
    -0.48
    addPreferredGap
    -0.48
    :])
    -0.46
    Lähteet
    -0.45
    addContainerGap
    -0.45
    omino
    -0.44
    POSITIVE LOGITS
    Carriera
    0.63
    yntaxException
    0.62
    GeoNames
    0.62
    ArrowToggle
    0.59
    HostException
    0.57
    Сюжет
    0.56
    Kedua
    0.56
    chooser
    0.54
    FunctionFlags
    0.54
    ymce
    0.54
    Activations Density 1.047%

    No Known Activations