© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14800
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to classifiers and their performance in classification tasks

    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
     ligiloj
    -0.66
    fjspx
    -0.62
     createStore
    -0.61
    UserScript
    -0.60
    osť
    -0.60
    addCriterion
    -0.58
     chng
    -0.57
     Pols
    -0.56
     Constitu
    -0.56
    omitempty
    -0.56
    POSITIVE LOGITS
    labels
    0.57
    answers
    0.55
     mục
    0.52
    Ecotoxicity
    0.52
    isdir
    0.51
    Externí
    0.51
     outcomes
    0.50
    UrlEncoded
    0.50
     classification
    0.50
     responses
    0.49
    Activations Density 0.647%

    No Known Activations