© 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. 2-GEMMASCOPE-RES-16K
    11. 4063
    Prev
    Next
    INDEX
    Explanations

    modal verbs and related phrases indicating necessity or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     present
    -0.59
     auto
    -0.57
    lein
    -0.53
     A
    -0.52
     gen
    -0.50
     final
    -0.50
    brainly
    -0.48
     choice
    -0.48
    一旁的
    -0.48
    Poppins
    -0.47
    POSITIVE LOGITS
     kann
    0.86
    Sucesor
    0.82
     können
    0.75
    expandindo
    0.69
     referrerpolicy
    0.66
     sollte
    0.66
     darf
    0.65
     müssen
    0.65
     muß
    0.65
     kommt
    0.64
    Activations Density 0.033%

    No Known Activations