© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 9338
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and database operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     away
    -0.45
    ScopeManager
    -0.43
    +:+
    -0.41
    verifyException
    -0.40
    Spoljašnje
    -0.40
    away
    -0.38
     opis
    -0.37
     ujednoznacz
    -0.37
    tvguidetime
    -0.36
     ivelany
    -0.36
    POSITIVE LOGITS
     insert
    3.23
     Insert
    3.11
     insertion
    3.06
     inserted
    2.98
     inserting
    2.94
     inserts
    2.91
    Insert
    2.83
    insert
    2.81
     Insertion
    2.75
     INSERT
    2.72
    Activations Density 1.079%

    No Known Activations