© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 338
    Prev
    Next
    INDEX
    Explanations

    statements involving abilities and achievements

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

    preceding "able," "can," or related terms

    np_acts-logits-general · gemini-2.0-flash

    ability to do or be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    belongs
    -0.55
    EROUS
    -0.53
    Greetings
    -0.47
    sschutz
    -0.47
    orea
    -0.47
     Spuren
    -0.46
    نامج
    -0.46
     parseFrom
    -0.46
     Bork
    -0.45
    asari
    -0.45
    POSITIVE LOGITS
     able
    1.99
     ability
    1.93
     Ability
    1.56
    Ability
    1.53
     Able
    1.43
    Able
    1.42
     capaz
    1.37
     capable
    1.32
     capaces
    1.27
     capability
    1.26
    Activations Density 0.525%

    No Known Activations