© 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. 7078
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to playful or humorous expressions

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

    Text after colons or em dashes

    np_acts-logits-general · gemini-2.0-flash

    mundane practical things, or general concepts

    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
     Hud
    -0.31
     Spuren
    -0.29
    tagHelperRunner
    -0.29
    /*
    -0.28
     tumbuh
    -0.28
    樣的
    -0.28
    mapStateToProps
    -0.28
    Cyfeiriadau
    -0.27
    DebuggerNonUser
    -0.27
     Mun
    -0.27
    POSITIVE LOGITS
    practical
    0.65
    ImageContext
    0.63
     nonUne
    0.63
     Administrativna
    0.63
     ſind
    0.61
    SerializedSize
    0.60
     للمعارف
    0.58
     ſche
    0.57
    delwed
    0.57
    Practical
    0.57
    Activations Density 0.229%

    No Known Activations