© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15493
    Prev
    Next
    INDEX
    Explanations

    terms related to the primary focus or main topics of discussion

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

    "Primarily", "mainly", or "mostly" followed by a reason

    np_acts-logits-general · gemini-2.0-flash

    reason or purpose

    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
     تضيفلها
    -0.59
     most
    -0.55
    səhifə
    -0.52
    原始内容存档于
    -0.52
    zzar
    -0.49
    LayoutStyle
    -0.49
    SequentialGroup
    -0.49
    addGap
    -0.48
    AsUp
    -0.48
    VIAF
    -0.48
    POSITIVE LOGITS
     kvůli
    0.49
     azért
    0.48
     dlatego
    0.43
     focused
    0.40
     due
    0.39
     ragioni
    0.39
    devším
    0.39
     darum
    0.39
     concernés
    0.37
     chodzi
    0.37
    Activations Density 0.292%

    No Known Activations