© 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. 6-GEMMASCOPE-RES-16K
    6. 783
    Prev
    Next
    INDEX
    Explanations

    expressions of preference or choice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.68
    Gil
    -0.65
     Audiodateien
    -0.64
     Al
    -0.61
    <h3>
    -0.60
     crise
    -0.60
     James
    -0.59
     Tom
    -0.59
     Gil
    -0.59
    brecht
    -0.59
    POSITIVE LOGITS
     Prefer
    1.91
     prefer
    1.88
    prefer
    1.84
     preference
    1.82
     preferred
    1.80
     prefers
    1.77
     Preferred
    1.75
     Preference
    1.74
     préfé
    1.72
     preferences
    1.68
    Activations Density 0.085%

    No Known Activations