© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2834
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "be" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "Be" at the beginning of sentences or phrases.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sepeda
    -0.44
     Süß
    -0.38
     hasard
    -0.38
    abstract
    -0.37
     disponibilités
    -0.37
    Globalization
    -0.36
    CharacterOffset
    -0.36
     cintas
    -0.36
    นัก
    -0.36
     berço
    -0.35
    POSITIVE LOGITS
     Be
    0.79
    Be
    0.78
    saraba
    0.67
     BE
    0.66
     Bew
    0.65
    BE
    0.60
    Bew
    0.56
     ***!
    0.56
    msgTypes
    0.55
    Bev
    0.52
    Activations Density 0.216%

    No Known Activations