© 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. 10792
    Prev
    Next
    INDEX
    Explanations

    references to specific entities and numbers in a document

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

    "The" followed by certain nouns

    np_acts-logits-general · gemini-2.0-flash

    the followed by a specific noun

    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
    ftagPool
    -0.67
    rungsseite
    -0.62
     HttpNotFound
    -0.58
     numberWith
    -0.55
    Filmografie
    -0.55
     preſent
    -0.53
    WebElementEntity
    -0.52
     AssemblyVersion
    -0.51
     WebDriverWait
    -0.51
     följande
    -0.50
    POSITIVE LOGITS
     company
    0.64
    company
    0.53
     automaker
    0.51
     snippetHide
    0.47
    公司的
    0.46
     compan
    0.44
     increasingly
    0.42
    公司
    0.42
     firm
    0.41
     its
    0.41
    Activations Density 0.625%

    No Known Activations