© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9468
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence-ending cues

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

    Followed by capitalized words or determiners

    np_acts-logits-general · gemini-2.0-flash

    demonstrative pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.64
    Rüyada
    -0.52
    BeginContext
    -0.46
     برانيه
    -0.45
     transférez
    -0.44
    GOTREF
    -0.44
    StoryboardSegue
    -0.43
     مرئيه
    -0.42
    assertArray
    -0.41
     esternos
    -0.40
    POSITIVE LOGITS
     this
    1.50
    これは
    1.46
     это
    1.30
     isso
    1.25
    これが
    1.11
     này
    1.09
     This
    1.09
    這是
    1.09
     questo
    1.06
     этого
    1.05
    Activations Density 1.522%

    No Known Activations