© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6486
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration or association between entities

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

    preceding "with" or similar conjunctions

    np_acts-logits-general · gemini-2.0-flash

    together with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.59
    windowFixed
    -0.56
     OFDb
    -0.52
    UnusedPrivate
    -0.50
     ProtoMessage
    -0.50
    TableBody
    -0.49
     saites
    -0.49
    DispatchToProps
    -0.47
    SaveChangesAsync
    -0.47
    impulan
    -0.45
    POSITIVE LOGITS
     junto
    0.41
    plaatst
    0.36
     наря
    0.36
     other
    0.36
     supli
    0.35
     geslacht
    0.34
     weitere
    0.34
     juntamente
    0.34
     refugiados
    0.34
     stejně
    0.33
    Activations Density 0.380%

    No Known Activations