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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13408
    Prev
    Next
    INDEX
    Explanations

    references to mutual relationships or interactions between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "each other"

    np_acts-logits-general · gemini-2.0-flash

    each other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.63
    utilisons
    -0.60
    таратура
    -0.55
     Protección
    -0.54
     ProtoMessage
    -0.52
    :✨
    -0.52
    fieldId
    -0.51
    Autoritní
    -0.49
     predominate
    -0.49
     DMG
    -0.48
    POSITIVE LOGITS
     other
    1.77
    other
    1.38
    others
    1.30
     others
    1.26
     otros
    1.22
     otras
    1.21
     andere
    1.18
     OTHER
    1.14
     outros
    1.14
    autres
    1.13
    Activations Density 0.079%

    No Known Activations