Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7332
    Prev
    Next
    INDEX
    Explanations

    Arabic characters or elements related to Arabic script

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.83
     nakalista
    -0.77
    parsedMessage
    -0.69
     AssemblyCulture
    -0.69
     doInBackground
    -0.68
    RegistryLite
    -0.66
    WriteTagHelper
    -0.64
    出版年
    -0.64
    writeFieldEnd
    -0.63
    PerformLayout
    -0.63
    POSITIVE LOGITS
    -------
    0.32
     expression
    0.31
     ع
    0.28
     accountId
    0.28
     attendant
    0.28
     це
    0.28
     ADS
    0.28
     bero
    0.27
    Šaltiniai
    0.27
    eventId
    0.26
    Activations Density 0.090%

    No Known Activations