© 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. 22-GEMMASCOPE-RES-16K
    11. 10620
    Prev
    Next
    INDEX
    Explanations

    subjects related to personal beliefs and commitments

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

    followed by "will" or its equivalent in other languages

    np_acts-logits-general · gemini-2.0-flash

    future outcome indicator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.68
     Wicidata
    -0.58
     betweenstory
    -0.50
     ब्रेकडाउन
    -0.50
     AssemblyTitle
    -0.44
    íná
    -0.44
    หมือน
    -0.43
    alite
    -0.43
    textAppearance
    -0.43
     eigentlich
    -0.43
    POSITIVE LOGITS
     will
    3.60
    will
    2.90
    Will
    2.44
     akan
    2.34
     sẽ
    2.30
     Will
    2.27
     WILL
    2.18
     zullen
    1.97
    WILL
    1.90
     будут
    1.72
    Activations Density 2.181%

    No Known Activations