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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8628
    Prev
    Next
    INDEX
    Explanations

    language indicating completed actions or prior experiences

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

    "already" or its translations

    np_acts-logits-general · gemini-2.0-flash

    already

    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
     Administrativna
    -0.49
    Portale
    -0.34
    次回は
    -0.33
    <%@
    -0.33
     ModelExpression
    -0.33
    Espèce
    -0.33
     jspb
    -0.32
    CharStream
    -0.32
     himo
    -0.32
    ביוגרפיה
    -0.32
    POSITIVE LOGITS
     already
    3.81
    already
    3.44
     Already
    3.39
    Already
    3.28
     ALREADY
    2.95
     이미
    2.64
     уже
    2.61
    ALREADY
    2.55
    すでに
    2.53
     allerede
    2.52
    Activations Density 1.595%

    No Known Activations