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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 9506
    Prev
    Next
    INDEX
    Explanations

    phrases that express concession or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.86
     autorytatywna
    -0.84
    Referencies
    -0.80
    TypedDataSet
    -0.79
    ArrowToggle
    -0.78
    tagHelperRunner
    -0.76
    utilisons
    -0.76
     Theſe
    -0.76
     myſelf
    -0.74
    OrBuilder
    -0.74
    POSITIVE LOGITS
     despite
    0.65
    Despite
    0.62
     Despite
    0.61
    (
    0.60
    WebServlet
    0.57
    despite
    0.57
    es
    0.56
    Dibrom
    0.56
    {
    0.55
     (
    0.54
    Activations Density 0.076%

    No Known Activations