© 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. 15-GEMMASCOPE-RES-16K
    6. 3018
    Prev
    Next
    INDEX
    Explanations

    instances of acknowledgment or recognition in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agisse
    -0.45
    
    -0.45
     virtuel
    -0.45
    ersatz
    -0.44
     Lengkap
    -0.43
     electrico
    -0.42
    verständnis
    -0.41
     edo
    -0.41
     cylindrical
    -0.41
    stridium
    -0.41
    POSITIVE LOGITS
     noticing
    1.12
     noticed
    1.11
    noticed
    0.97
     noticeable
    0.96
     notice
    0.96
     noted
    0.90
    notice
    0.87
     notices
    0.87
     Notice
    0.86
    Notice
    0.84
    Activations Density 0.284%

    No Known Activations