© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2782
    Prev
    Next
    INDEX
    Explanations

    references to the reader or the second person in conversational text

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

    "You" followed by a modal verb

    np_acts-logits-general · gemini-2.0-flash

    you followed by modal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.49
    штей
    -0.39
    styleType
    -0.37
     COIN
    -0.37
     Rid
    -0.37
     Sik
    -0.37
    vors
    -0.37
    Shi
    -0.36
    gines
    -0.36
    mor
    -0.35
    POSITIVE LOGITS
     probably
    0.64
    Probably
    0.58
     dovrebbero
    0.54
     provavelmente
    0.54
     Probably
    0.54
    probably
    0.54
     probablemente
    0.54
     prolly
    0.54
     probabilmente
    0.54
     devront
    0.52
    Activations Density 0.196%

    No Known Activations