© 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. 3541
    Prev
    Next
    INDEX
    Explanations

    Czech words related to aspects of evaluation or classification

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

    Text after certain punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    lakše, Lac, any printer

    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
    /
    -0.64
    ,
    -0.64
    <eos>
    -0.58
    .
    -0.58
    ;
    -0.57
     
    -0.54
    ?
    -0.53
    $
    -0.53
    (
    -0.52
    вості
    -0.52
    POSITIVE LOGITS
     '\\;'
    1.06
    WithIOException
    1.02
    oredCriteria
    0.93
     doubtnut
    0.85
    ThemeOverlay
    0.80
    енча
    0.80
     ſind
    0.79
     CanadaChoose
    0.79
    ]='\
    0.78
    Bibliografía
    0.77
    Activations Density 0.024%

    No Known Activations