© 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. 25-GEMMASCOPE-RES-16K
    11. 10644
    Prev
    Next
    INDEX
    Explanations

    contractions and possessive forms of pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     will
    -0.68
     оригіналу
    -0.58
    abestanden
    -0.56
     WILL
    -0.53
    BufferException
    -0.50
    ">—
    -0.49
     otomatig
    -0.48
     ͡°
    -0.48
     Will
    -0.47
     are
    -0.47
    POSITIVE LOGITS
    ve
    1.73
    Ive
    0.87
     Ive
    0.86
     للمعارف
    0.83
    been
    0.76
    VE
    0.76
     ve
    0.72
     ive
    0.70
    has
    0.67
    webElementXpaths
    0.66
    Activations Density 0.110%

    No Known Activations