© 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. 12-GEMMASCOPE-RES-16K
    6. 9573
    Prev
    Next
    INDEX
    Explanations

    phrases related to product appreciation and usage experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sukker
    -0.40
    scalatest
    -0.38
     coaches
    -0.36
     chambres
    -0.36
    agents
    -0.36
     supporting
    -0.36
     dépenses
    -0.36
     matrices
    -0.36
    )];
    
    -0.36
     woning
    -0.35
    POSITIVE LOGITS
    SerializedSize
    0.54
    protoimpl
    0.52
    fjspx
    0.50
     Савезне
    0.45
     aDecoder
    0.44
    Tembelea
    0.43
     CYTHON
    0.43
     Privacidade
    0.42
    RepeatedField
    0.42
     createSlice
    0.41
    Activations Density 0.153%

    No Known Activations