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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6775
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicative of future intentions or actions

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

    expressions of future intentions and commitments

    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
     Jefus
    -1.00
    存于互联网档案馆
    -0.98
     itſelf
    -0.95
     Majefty
    -0.93
     Monfieur
    -0.90
     ſche
    -0.90
     myſelf
    -0.89
     houſe
    -0.89
     Perſ
    -0.88
    ſelf
    -0.88
    POSITIVE LOGITS
     will
    1.39
     WILL
    1.15
     Will
    1.11
    will
    1.03
     be
    1.00
    WILL
    0.99
    Will
    0.96
     can
    0.92
     have
    0.85
     not
    0.82
    Activations Density 0.135%

    No Known Activations