© 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. 12637
    Prev
    Next
    INDEX
    Explanations

    repeated conjunctions and phrases indicating collective actions or thoughts

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

    Imperative verbs

    np_acts-logits-general · gemini-2.0-flash

    connecting clauses

    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
    basicConfig
    -0.50
    所以
    -0.38
     Therefore
    -0.37
    故
    -0.36
     hoeft
    -0.36
     所以
    -0.35
     springfox
    -0.35
     therefore
    -0.35
     now
    -0.35
    所以我
    -0.35
    POSITIVE LOGITS
     let
    0.98
     remember
    0.91
     please
    0.89
     enjoy
    0.86
     try
    0.84
     watch
    0.79
     hãy
    0.78
    please
    0.76
     see
    0.75
     ask
    0.72
    Activations Density 0.174%

    No Known Activations