© 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. 10676
    Prev
    Next
    INDEX
    Explanations

    concepts related to market dynamics and fluctuations

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

    Movement between two points

    np_acts-logits-general · gemini-2.0-flash

    moving back and forth

    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
    webElementXpaths
    -0.48
    StoreMessageInfo
    -0.46
    IntoConstraints
    -0.46
    StoryboardSegue
    -0.46
    TypedDataSet
    -0.45
     snippetHide
    -0.44
     незавершена
    -0.43
    richTextPanel
    -0.43
    🔕
    -0.43
    ductory
    -0.41
    POSITIVE LOGITS
     alternating
    1.34
     fluctuating
    1.23
     switching
    1.21
     alternately
    1.20
     wechsel
    1.16
     alternates
    1.06
     fluctuate
    1.06
     fluctu
    1.05
     alternation
    1.05
     altern
    1.04
    Activations Density 0.846%

    No Known Activations