© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8882
    Prev
    Next
    INDEX
    Explanations

    instances of the word "or" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     auffi
    -0.55
     ſind
    -0.54
    iſt
    -0.53
     archa
    -0.52
    eleste
    -0.52
     surla
    -0.52
    ⪜
    -0.51
    entance
    -0.51
    dalena
    -0.51
    ſcher
    -0.51
    POSITIVE LOGITS
     или
    3.05
     eller
    3.00
     atau
    2.97
     alebo
    2.95
     oder
    2.91
     hoặc
    2.91
     vagy
    2.89
     or
    2.72
     nebo
    2.72
     või
    2.59
    Activations Density 0.326%

    No Known Activations