© 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. 14680
    Prev
    Next
    INDEX
    Explanations

    references to specific entities and their attributes in various contexts

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

    Tokens after "how", "series", and "logo"

    np_acts-logits-general · gemini-2.0-flash

    how to, usual, portal

    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
    savefig
    -0.40
    writeField
    -0.40
    gemini
    -0.40
     cucchiai
    -0.39
    GEBURTS
    -0.39
     dévelo
    -0.39
    jsxFileName
    -0.38
    TryDecodeAsNil
    -0.38
    cshtml
    -0.38
     autorytatywna
    -0.37
    POSITIVE LOGITS
    ValueStyle
    0.61
    usual
    0.59
     usual
    0.55
    Usual
    0.51
     referenties
    0.49
    principalTable
    0.48
     Normally
    0.46
    RegistryLite
    0.46
    Normally
    0.45
    RTDA
    0.44
    Activations Density 0.653%

    No Known Activations