© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9456
    Prev
    Next
    INDEX
    Explanations

    concepts related to foundational elements and structures within various contexts

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

    like "foundation" or "basis"

    np_acts-logits-general · gemini-2.0-flash

    basis and foundation for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActionCreators
    -0.56
    \{\\
    -0.54
    ContentAsync
    -0.54
     doby
    -0.50
    Fordítás
    -0.50
    ymce
    -0.48
    IsMutable
    -0.48
     sportif
    -0.47
     disponibilités
    -0.47
     miscellaneous
    -0.47
    POSITIVE LOGITS
     foundation
    1.02
     basis
    0.85
     foundations
    0.84
     Grundlage
    0.82
     foundational
    0.82
     Basis
    0.81
     base
    0.81
     BASIS
    0.80
     underlying
    0.79
    Basis
    0.77
    Activations Density 0.385%

    No Known Activations