© 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. 12280
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and data types in code

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

    Code snippets and system references

    np_acts-logits-general · gemini-2.0-flash

    actor `()` and `class`

    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
     élé
    -0.30
     Mexique
    -0.29
     Alabama
    -0.29
     kö
    -0.29
     Ken
    -0.27
     Kenyan
    -0.27
     名古屋
    -0.27
     obtend
    -0.26
     Queensland
    -0.26
     puesto
    -0.25
    POSITIVE LOGITS
     betweenstory
    1.05
     Srinagar
    0.97
     Jammu
    0.95
     Kashmir
    0.89
    ագրություններ
    0.85
     AssemblyCulture
    0.76
    antMatchers
    0.73
     NavController
    0.71
    MLLoader
    0.68
    ؠ
    0.68
    Activations Density 0.057%

    No Known Activations