© 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. 39-GEMMASCOPE-RES-16K
    6. 812
    Prev
    Next
    INDEX
    Explanations

    technical terms related to semiconductor manufacturing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coun
    -0.38
     Вікі
    -0.36
     ब्रेकडाउन
    -0.34
    Estat
    -0.33
     MainAxisSize
    -0.32
     Brou
    -0.32
     DataGridView
    -0.30
    WaitGroup
    -0.30
     Ble
    -0.30
     Catch
    -0.30
    POSITIVE LOGITS
     deposition
    1.30
     Deposition
    1.17
     depositing
    1.14
     deposited
    1.10
     deposit
    1.05
    deposit
    1.05
     depositions
    1.04
    Deposit
    1.00
     Deposit
    0.96
     dépôt
    0.95
    Activations Density 1.451%

    No Known Activations