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. 2-GEMMASCOPE-RES-16K
    6. 3634
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "operator" in various contexts

    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
    mybatisplus
    -0.63
     vært
    -0.62
     ​​
    -0.55
    lebo
    -0.54
    anceled
    -0.53
    zło
    -0.53
    errHandler
    -0.52
    birthdate
    -0.51
    pakah
    -0.50
    thiet
    -0.50
    POSITIVE LOGITS
     acrylique
    0.86
    Datuak
    0.80
     Lacy
    0.74
    spesies
    0.74
    +#+#
    0.73
    Clik
    0.72
    сылкі
    0.72
    herin
    0.72
    ReusableCell
    0.71
     Eleg
    0.71
    Activations Density 0.081%

    No Known Activations