© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12654
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to engineering and circuit design

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

    Problems, difficulties, and reduction

    np_acts-logits-general · gemini-2.0-flash

    issues, problems, and abnormalities

    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
     AssemblyVersion
    -0.58
     حض
    -0.50
    clerView
    -0.49
    ########.
    -0.48
    logeny
    -0.47
     Alber
    -0.47
    MigrationBuilder
    -0.45
    +:+
    -0.45
    waitKey
    -0.45
    atrician
    -0.45
    POSITIVE LOGITS
     stronę
    0.41
     dział
    0.41
    avons
    0.40
     rzecz
    0.40
    éviter
    0.39
     urodz
    0.38
     ruchu
    0.38
    aucune
    0.38
     bezpieczeństwa
    0.38
     abnormal
    0.37
    Activations Density 0.299%

    No Known Activations