© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7208
    Prev
    Next
    INDEX
    Explanations

    code-related commands and user input interactions

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

    Receiving user input (from keyboard/console)

    np_acts-logits-general · gemini-2.0-flash

    reading user input

    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
    AddTagHelper
    -0.54
    httphttps
    -0.51
     iconLine
    -0.50
     صوتيه
    -0.49
     TestBed
    -0.49
    */].
    -0.48
    AndroidJUnit
    -0.48
     мәкал
    -0.47
    TestingModule
    -0.47
    ttemberg
    -0.43
    POSITIVE LOGITS
     getInput
    0.47
     input
    0.47
     saisie
    0.47
    Input
    0.44
    input
    0.44
    PerformLayout
    0.44
     Input
    0.43
    ReadLine
    0.42
    getInput
    0.42
    INPUT
    0.41
    Activations Density 0.197%

    No Known Activations