© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30440
    Prev
    Next
    INDEX
    Explanations

    phrases that describe relationships or dependencies between systems

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

    interaction or relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.82
     disambiguazione
    -0.75
    Хьажоргаш
    -0.73
    IVEREF
    -0.72
    MemoryWarning
    -0.71
    expandindo
    -0.70
     كومونز
    -0.70
    AsUp
    -0.69
    MLLoader
    -0.66
    новниш
    -0.66
    POSITIVE LOGITS
     unknownFields
    0.62
     dialogue
    0.52
     interaction
    0.52
    engage
    0.49
     dialog
    0.43
     interactions
    0.41
     conversation
    0.41
    对话
    0.41
     interact
    0.40
    DIALOG
    0.40
    Activations Density 0.135%

    No Known Activations