© 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. 1730
    Prev
    Next
    INDEX
    Explanations

    terms related to changes or adjustments in systems and processes

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

    after "of", "to", or "on"

    np_acts-logits-general · gemini-2.0-flash

    dose of selected patients

    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
    ContentAsync
    -0.51
    таратура
    -0.48
     transfieras
    -0.48
     otomatig
    -0.46
     utafitiHapana
    -0.44
    RTSC
    -0.42
    +:+
    -0.41
    HasForeignKey
    -0.41
    󠁣
    -0.40
    出版年
    -0.40
    POSITIVE LOGITS
    __()
    0.38
    SearchParams
    0.38
    ViewInit
    0.37
     Gob
    0.36
    不成
    0.35
     BrowserModule
    0.35
    HttpFoundation
    0.35
    cambrian
    0.35
    ArgsConstructor
    0.34
    \{\\
    0.34
    Activations Density 1.281%

    No Known Activations