Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6769
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that emphasize beliefs about reality and truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Relatively
    -0.58
     Somewhat
    -0.58
    canestro
    -0.56
     dovuto
    -0.55
    gaande
    -0.54
     particolarmente
    -0.54
     Slightly
    -0.53
    lably
    -0.52
     dość
    -0.52
    }>;
    -0.52
    POSITIVE LOGITS
     life
    0.89
     everyone
    0.88
     nobody
    0.84
     humans
    0.81
     every
    0.81
     nothing
    0.79
    everyone
    0.77
     everybody
    0.74
    Everyone
    0.74
     human
    0.70
    Activations Density 0.495%

    No Known Activations