© 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. 33-GEMMASCOPE-RES-16K
    11. 8158
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potentiality or feasibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.50
    исленность
    -0.45
    पया
    -0.43
     Lingkungan
    -0.43
    yntaxException
    -0.42
    InjectAttribute
    -0.42
     InputDecoration
    -0.41
     kasarigan
    -0.39
     beginnetje
    -0.39
    Бахар
    -0.39
    POSITIVE LOGITS
     possible
    2.72
    possible
    2.41
     Possible
    2.20
    Possible
    2.19
     POSSIBLE
    2.02
     posible
    2.00
     possível
    1.93
     möglich
    1.91
     possibile
    1.91
     possibility
    1.90
    Activations Density 0.575%

    No Known Activations