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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 9197
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "OR" as it relates to logical operations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     Vikipedi
    -0.54
    ubi
    -0.47
    masin
    -0.47
    intense
    -0.45
     FEEDBACK
    -0.44
     picky
    -0.43
     hotly
    -0.42
    pius
    -0.42
    pex
    -0.41
    🏻
    -0.41
    POSITIVE LOGITS
     OR
    0.76
     strong
    0.66
     mutual
    0.58
     strict
    0.56
    djangoproject
    0.54
    OR
    0.52
    strong
    0.51
    CrossRef
    0.51
    SharedCtor
    0.50
    Strong
    0.50
    Activations Density 0.091%

    No Known Activations