© 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. 2012
    Prev
    Next
    INDEX
    Explanations

    programming commands and constructs in code snippets

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

    Code related to "hello world" examples

    np_acts-logits-general · gemini-2.0-flash

    hello world ping

    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
     Interessen
    -0.27
    einander
    -0.27
     interesan
    -0.27
     Vorsch
    -0.27
     Ausstattung
    -0.26
     réaliste
    -0.26
     Einbau
    -0.25
     Rücks
    -0.25
     Ursachen
    -0.25
     toalha
    -0.24
    POSITIVE LOGITS
    الحياه
    0.73
     Biôgrafia
    0.70
    ngdoc
    0.68
     kasarigan
    0.66
     noDo
    0.66
    RotationOrder
    0.65
    InstrumentedTest
    0.65
    #+#
    0.65
    tagext
    0.65
    MIDDLEWARE
    0.63
    Activations Density 0.169%

    No Known Activations