© 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. 10707
    Prev
    Next
    INDEX
    Explanations

    references to organizations and individuals involved in education policy or advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    audiovisuel
    -0.35
     OFDb
    -0.34
     descar
    -0.33
    脚注の使い方
    -0.32
    úblico
    -0.32
     Jharkhand
    -0.31
     leh
    -0.31
     Appalachian
    -0.31
    UnknownFieldSet
    -0.31
    richTextPanel
    -0.30
    POSITIVE LOGITS
     California
    1.48
     Los
    1.45
    California
    1.38
     UCLA
    1.27
    Los
    1.27
     CALIFORNIA
    1.24
     Pasadena
    1.22
     Califor
    1.20
     california
    1.19
     Californian
    1.19
    Activations Density 0.834%

    No Known Activations