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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 16131
    Prev
    Next
    INDEX
    Explanations

    expressions of friendliness and politeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maș
    -0.72
    enumi
    -0.71
    subplots
    -0.70
     Truths
    -0.66
    ;#
    -0.65
    <h5>
    -0.64
    lanzen
    -0.63
     JComboBox
    -0.63
     Victims
    -0.63
    Cars
    -0.62
    POSITIVE LOGITS
     friendly
    2.13
     Friendly
    2.04
    Friendly
    1.95
    friendly
    1.85
     friendliness
    1.59
     unfriendly
    1.46
     vriende
    1.13
     freundlich
    1.13
     freundlichen
    1.12
     freund
    1.11
    Activations Density 0.052%

    No Known Activations