© 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. 18-GEMMASCOPE-RES-16K
    6. 7023
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical notations within a technical context

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

    Mathematical expressions with numbers and symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Literatura
    -0.57
     povezave
    -0.49
    DataContract
    -0.47
    ————————————————
    -0.46
    уза
    -0.46
    filepath
    -0.45
    uesia
    -0.45
    Bare
    -0.45
    ссора
    -0.44
    RuleContext
    -0.44
    POSITIVE LOGITS
    SuppressLint
    0.74
    
    0.72
    +#+#
    0.72
     dimensional
    0.69
    addContainerGap
    0.67
     sided
    0.63
    ::_('
    0.62
     legged
    0.61
     NSCoder
    0.61
    dimensional
    0.60
    Activations Density 0.886%

    No Known Activations