© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1851
    Prev
    Next
    INDEX
    Explanations

    institutions, organizations, and government-related entities

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

    Appears before "of" and refers to institutions

    np_acts-logits-general · gemini-2.0-flash

    institutions followed by of

    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
    attuale
    -0.45
    ,
    -0.42
    ganggu
    -0.39
     réun
    -0.38
     aimez
    -0.37
     incendios
    -0.37
     serez
    -0.37
     cervello
    -0.36
     réellement
    -0.36
     actual
    -0.36
    POSITIVE LOGITS
    ValueStyle
    0.79
    DockStyle
    0.75
    OGND
    0.71
    adpleegd
    0.69
     trattano
    0.65
    Personendaten
    0.64
    Portail
    0.64
    CloseOperation
    0.63
    (!__
    0.63
    LEncoder
    0.62
    Activations Density 0.342%

    No Known Activations