© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12038
    Prev
    Next
    INDEX
    Explanations

    references to relationships, interactions, and definitions within a structured context, particularly focusing on entities and their connections

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

    Text within parentheses, brackets, or quotes

    np_acts-logits-general · gemini-2.0-flash

    words or phrases enclosed in asterisks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.82
     utafitiHapana
    -0.78
    niſſe
    -0.77
    <unused28>
    -0.74
    <unused14>
    -0.74
    <unused8>
    -0.74
    [@BOS@]
    -0.74
    <unused68>
    -0.74
    <unused23>
    -0.73
    <unused41>
    -0.73
    POSITIVE LOGITS
     Staates
    0.42
     męski
    0.39
     Volkes
    0.38
     venganza
    0.38
     męska
    0.38
    niająca
    0.37
     bolsillos
    0.37
     sogen
    0.37
     jueces
    0.36
     Versuche
    0.36
    Activations Density 0.522%

    No Known Activations