© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11371
    Prev
    Next
    INDEX
    Explanations

    references to conservation and environmental planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ≔
    -0.29
     modes
    -0.25
     mode
    -0.25
     we
    -0.23
     am
    -0.23
    raum
    -0.23
     edge
    -0.22
    <bos>
    -0.21
     fellow
    -0.21
    ('/:
    -0.21
    POSITIVE LOGITS
     فريبيس
    0.88
     disambiguazione
    0.87
     تضيفلها
    0.84
    bootstrapcdn
    0.79
    EndContext
    0.75
     unknownFields
    0.75
    ViewFeatures
    0.74
     StringTokenizer
    0.71
     kasarigan
    0.70
    orestation
    0.70
    Activations Density 0.396%

    No Known Activations