© 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. 2052
    Prev
    Next
    INDEX
    Explanations

    structured references and publications related to specific organizations or entities

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

    Appearing in years or numerical data

    np_acts-logits-general · gemini-2.0-flash

    years and formats

    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
    RenderAtEndOf
    -0.70
    AutoScaleMode
    -0.69
    InputBorder
    -0.69
    kloped
    -0.68
    >>()
    -0.67
     дописавши
    -0.67
     '+':
    -0.62
     otomatig
    -0.62
    ValueStyle
    -0.62
    ffindor
    -0.62
    POSITIVE LOGITS
     but
    0.68
     realizarse
    0.52
     originally
    0.47
    名叫
    0.46
     bertujuan
    0.45
     initially
    0.44
     donc
    0.44
    而来
    0.43
    HEET
    0.43
     juzgar
    0.43
    Activations Density 0.671%

    No Known Activations