© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 749
    Prev
    Next
    INDEX
    Explanations

    dialogue and speech markers in text

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

    Quotation marks followed by imperative verbs

    np_acts-logits-general · gemini-2.0-flash

    quotes and commands

    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
     similarly
    -0.54
    Additionally
    -0.52
    /*!
    -0.51
     legit
    -0.49
    Moreover
    -0.47
    確かに
    -0.46
     Notably
    -0.46
    Conversely
    -0.46
    余談
    -0.46
     irl
    -0.46
    POSITIVE LOGITS
     Look
    1.24
     Come
    1.24
    Come
    1.19
    Look
    1.17
     come
    0.99
     Give
    0.98
     look
    0.97
     Get
    0.96
     COME
    0.96
    look
    0.96
    Activations Density 0.223%

    No Known Activations