© 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. 12289
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their statements or roles in discussions

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

    Name before the word "said"

    np_acts-logits-general · gemini-2.0-flash

    reporting someone said

    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
    tvguidetime
    -0.56
    mybatisplus
    -0.55
     चीज़ों
    -0.54
     AssemblyVersion
    -0.52
    tagPool
    -0.52
     linkovi
    -0.52
     Benth
    -0.51
     iconLine
    -0.49
    Javadoc
    -0.48
    DataSnapshot
    -0.48
    POSITIVE LOGITS
     said
    1.08
    said
    0.60
     mengatakan
    0.45
     says
    0.44
     noted
    0.44
     sagde
    0.44
     likened
    0.43
    Said
    0.41
     कहा
    0.41
     faid
    0.41
    Activations Density 0.231%

    No Known Activations