© 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. 3-GEMMASCOPE-RES-16K
    6. 8076
    Prev
    Next
    INDEX
    Explanations

    the concept of completion or finalization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    üyada
    -0.46
    Билгалдахарш
    -0.42
     BigInteger
    -0.40
    assador
    -0.40
     pinulongan
    -0.40
     UserDao
    -0.40
     taxes
    -0.39
    Superclass
    -0.38
     larynx
    -0.38
    MouseListener
    -0.38
    POSITIVE LOGITS
     completed
    3.28
     completing
    3.19
     completion
    3.19
     Completion
    3.00
    completed
    2.97
     Completed
    2.95
     Completing
    2.95
     completes
    2.95
    Completed
    2.80
    completion
    2.77
    Activations Density 0.110%

    No Known Activations