© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 7364
    Prev
    Next
    INDEX
    Explanations

    terms related to interactions and processes involving exchange or influence

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

    "Interaction" or "interact" and subsequent related words

    np_acts-logits-general · gemini-2.0-flash

    interaction between or with

    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
     defaultstate
    -0.81
    -------
    -0.64
    RepeatedField
    -0.62
    archi
    -0.61
    »։
    -0.61
    isContained
    -0.61
    rceil
    -0.59
    cester
    -0.59
     TDC
    -0.59
    colgroup
    -0.58
    POSITIVE LOGITS
     interactions
    0.91
    Interactions
    0.83
     Interactions
    0.80
     interaction
    0.78
    interactions
    0.75
     Interaction
    0.75
     Interact
    0.72
     interact
    0.70
    interaction
    0.69
     interacción
    0.69
    Activations Density 0.080%

    No Known Activations