© 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. 10737
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal responsibilities and proceedings

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

    a challenge or difficulty

    np_acts-logits-general · gemini-2.0-flash

    easy task, point on, speak for

    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
     Owing
    -0.41
     curated
    -0.40
     incentiv
    -0.40
     prioritise
    -0.40
     learnt
    -0.39
     fridge
    -0.39
     optimisation
    -0.39
     screenshots
    -0.38
    Diwedd
    -0.38
     curation
    -0.38
    POSITIVE LOGITS
    faßt
    0.68
     muß
    0.64
     daß
    0.60
    addCriterion
    0.58
    luß
    0.56
     mußte
    0.56
    +#+
    0.56
    SpringRunner
    0.56
    Personendaten
    0.55
     opportunità
    0.54
    Activations Density 1.955%

    No Known Activations