© 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. 18-GEMMASCOPE-RES-16K
    11. 4539
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and operations related to maximizing or minimizing values

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

    "max" or "min" functions and related terms

    np_acts-logits-general · gemini-2.0-flash

    min or max values

    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
    principalTable
    -0.72
     jScrollPane
    -0.64
    Personensuche
    -0.60
    brainly
    -0.58
     jLabel
    -0.58
    BarButtonItem
    -0.55
    UNRELATED
    -0.54
    نیم
    -0.54
     חיצוניים
    -0.54
    FORME
    -0.53
    POSITIVE LOGITS
     minimum
    1.66
    minimum
    1.46
     min
    1.41
     Minimum
    1.37
    min
    1.31
     MINIMUM
    1.31
    Minimum
    1.30
     mínimo
    1.28
     minimo
    1.27
    Min
    1.22
    Activations Density 0.362%

    No Known Activations