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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 13707
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and emotional connections

    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
    Giving
    -0.54
     giving
    -0.48
     ervan
    -0.47
     Giving
    -0.47
     있어
    -0.46
     ligiloj
    -0.45
    glLoadIdentity
    -0.45
    Conduct
    -0.45
     kijken
    -0.45
     agir
    -0.45
    POSITIVE LOGITS
     sorely
    0.68
     hopefully
    0.67
     zuvor
    0.67
     thankfully
    0.66
    extAlignment
    0.63
    +#+#
    0.63
     luckily
    0.63
    "]));
    0.62
    RegisterType
    0.61
     later
    0.61
    Activations Density 0.289%

    No Known Activations