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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 6289
    Prev
    Next
    INDEX
    Explanations

    mentions of friendship and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baga
    -0.89
     Theaters
    -0.82
    oriasis
    -0.81
     cappello
    -0.79
    shtml
    -0.78
    jména
    -0.76
    zugehen
    -0.75
     disponibilités
    -0.74
     Hv
    -0.73
     silenzio
    -0.72
    POSITIVE LOGITS
     friends
    1.74
     Friends
    1.66
    friends
    1.58
     FRIENDS
    1.52
    Friends
    1.48
     friend
    1.47
     Friend
    1.44
     FRIEND
    1.37
    Friend
    1.33
     Friendship
    1.25
    Activations Density 0.057%

    No Known Activations