© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14274
    Prev
    Next
    INDEX
    Explanations

    details and specifications related to electronic devices, specifically audio and visual equipment

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

    following capitalized words

    np_acts-logits-general · gemini-2.0-flash

    Barracuda, Motif, Africa Twin, Byrd Apartments

    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
    setVerticalGroup
    -0.63
    rrggbb
    -0.62
     utafitiHapana
    -0.58
     CURLOPT
    -0.51
    SequentialGroup
    -0.50
    toupper
    -0.50
     @"/
    -0.49
    undet
    -0.49
    CJK
    -0.47
    hassee
    -0.47
    POSITIVE LOGITS
     series
    0.68
     mijne
    0.67
     Series
    0.64
    onAttach
    0.63
     Majefty
    0.63
    series
    0.61
     poffe
    0.61
     série
    0.59
     fuper
    0.59
     uſed
    0.58
    Activations Density 0.383%

    No Known Activations