© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10709
    Prev
    Next
    INDEX
    Explanations

    instances of numerical ranges and scientific notations

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

    Numbers in brackets (citations/references)

    np_acts-logits-general · gemini-2.0-flash

    ranges and lists

    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
    IUrlHelper
    -0.72
     snippetHide
    -0.62
     resourceCulture
    -0.61
     CreateTagHelper
    -0.58
     surla
    -0.57
    SharedDtor
    -0.57
     Biôgrafia
    -0.56
    HtmlAttribute
    -0.55
     ExecuteAsync
    -0.54
     OFDb
    -0.54
    POSITIVE LOGITS
     लेकर
    0.49
    enumi
    0.43
    horabuena
    0.43
    ถึง
    0.36
    izante
    0.34
    run
    0.34
    bootstrapcdn
    0.33
     peine
    0.31
    engagent
    0.30
    complex
    0.30
    Activations Density 0.444%

    No Known Activations