© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13267
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical structures and cooperative systems

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

    unions, fusions, or intersections

    np_acts-logits-general · gemini-2.0-flash

    between or product of

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    SourceChecksum
    -0.57
     ThemeData
    -0.56
     imageNamed
    -0.56
    ⓧ
    -0.55
     defStyleAttr
    -0.54
    caid
    -0.54
    gartner
    -0.53
     Verso
    -0.53
    مراجع
    -0.52
     behold
    -0.52
    POSITIVE LOGITS
     between
    1.41
    between
    1.17
     между
    1.15
     Between
    1.07
     BETWEEN
    1.03
    Between
    1.02
     mellan
    0.98
     antara
    0.97
     betwixt
    0.94
     tussen
    0.91
    Activations Density 1.056%

    No Known Activations