© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3091
    Prev
    Next
    INDEX
    Explanations

    terms related to flatness or lack of elevation

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

    references to "flat" in various contexts, such as flat tax, flat fee, flat landscape, or flat surface.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ragamo
    -0.77
    featureID
    -0.73
    $_['
    -0.67
     NavController
    -0.66
     queſta
    -0.64
     czeka
    -0.61
    belongsTo
    -0.60
     czuj
    -0.60
     berço
    -0.60
     Berries
    -0.59
    POSITIVE LOGITS
     flat
    0.84
     Flat
    0.84
    flat
    0.81
     FLAT
    0.80
    Flat
    0.78
     Straight
    0.75
     straight
    0.74
     round
    0.69
    FLAT
    0.68
    Round
    0.67
    Activations Density 0.133%

    No Known Activations