© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12041
    Prev
    Next
    INDEX
    Explanations

    download-related terms for mobile games and applications

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

    Preceding words of app versions and game titles

    np_acts-logits-general · gemini-2.0-flash

    APK downloads and versions

    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
    évaluateur
    -0.56
    Datuak
    -0.49
     pinulongan
    -0.48
     gainera
    -0.44
     refin
    -0.44
     captive
    -0.43
     constru
    -0.43
    sens
    -0.42
     snowflakes
    -0.42
    setVerticalGroup
    -0.42
    POSITIVE LOGITS
    ">//
    0.51
     >=",
    0.44
    ValueStyle
    0.43
     MessageBoxIcon
    0.42
     resourceCulture
    0.41
     kræ
    0.40
    bootstrapcdn
    0.40
     arcilla
    0.39
    EDEFAULT
    0.39
    seamnă
    0.38
    Activations Density 0.071%

    No Known Activations