© 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. 7052
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data structure definitions

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

    Code, programming, or data structures

    np_acts-logits-general · gemini-2.0-flash

    code snippets

    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
     /\.(
    -0.54
     חיצוניים
    -0.53
     TextFormField
    -0.52
    saraba
    -0.51
    AsUp
    -0.49
     MessageBoxIcon
    -0.48
     Wicidata
    -0.48
     Jacobian
    -0.47
     stringBy
    -0.47
     meriva
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.60
    InSection
    0.56
    old
    0.51
     temp
    0.51
     kaarangay
    0.51
    Géographie
    0.50
    Donnerstag
    0.49
     x
    0.49
    _]
    0.48
    ValueStyle
    0.48
    Activations Density 0.991%

    No Known Activations