© 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. 10025
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comparison or contrasting characteristics

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

    Preposition "with" followed by positive attribute

    np_acts-logits-general · gemini-2.0-flash

    describing the manner of action

    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
     للمعارف
    -0.70
     '\\;'
    -0.66
    djangoproject
    -0.62
     uintptr
    -0.59
     Réponses
    -0.58
    atini
    -0.56
    ########.
    -0.56
     uParam
    -0.55
     AssemblyTitle
    -0.53
     kasarigan
    -0.53
    POSITIVE LOGITS
     ease
    1.00
     precision
    0.98
     regularity
    0.88
     confidence
    0.87
     gusto
    0.86
     accuracy
    0.83
     impunity
    0.81
     vigor
    0.80
    precision
    0.79
     efficiency
    0.72
    Activations Density 0.168%

    No Known Activations