© 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-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 14247
    Prev
    Next
    INDEX
    Explanations

    instances of the modal verb "can" indicating possibility or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
    <bos>
    -0.39
     fellow
    -0.36
     BOY
    -0.34
     the
    -0.33
     Jour
    -0.32
    ze
    -0.32
     compañ
    -0.31
    ī
    -0.31
     Ord
    -0.31
    __
    -0.31
    POSITIVE LOGITS
     can
    1.29
    Can
    1.11
     Can
    1.08
     canst
    1.05
    can
    1.03
     pouvons
    0.96
     pouvez
    0.95
     CAN
    0.94
     può
    0.93
     ניתן
    0.92
    Activations Density 0.344%

    No Known Activations