© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6518
    Prev
    Next
    INDEX
    Explanations

    expressions of affection or love

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

    expressions of enthusiasm or positive sentiment using the word "love".

    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
     Quay
    -0.44
    mHandler
    -0.43
     portico
    -0.43
    XHR
    -0.43
     Shorts
    -0.43
     Cigar
    -0.43
     barbarians
    -0.43
    ▐
    -0.43
     briskly
    -0.43
    CGContext
    -0.41
    POSITIVE LOGITS
     LOVE
    1.08
     love
    1.06
    Love
    1.02
    LOVE
    1.00
     Love
    0.97
    love
    0.95
    Loves
    0.91
     Loves
    0.90
     loves
    0.84
     loved
    0.82
    Activations Density 0.036%

    No Known Activations