© 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. 1642
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and structures related to state management

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

    Code, variables, or counters

    np_acts-logits-general · gemini-2.0-flash

    state tracking and estimation

    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
    TargetException
    -0.64
     CreateTagHelper
    -0.59
    AnimationsModule
    -0.47
    URLException
    -0.47
    ंदीखरीदारी
    -0.46
     PSE
    -0.45
     kasarigan
    -0.44
     surla
    -0.44
    Насе
    -0.43
    KommentareTeilen
    -0.43
    POSITIVE LOGITS
    FDRE
    0.46
    Datuak
    0.45
    новништво
    0.41
     mantenerse
    0.35
    '&:
    0.35
     labios
    0.35
     acumula
    0.35
     unbroken
    0.34
     cuillère
    0.34
     kept
    0.34
    Activations Density 0.425%

    No Known Activations