© 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. 33-GEMMASCOPE-RES-16K
    6. 8702
    Prev
    Next
    INDEX
    Explanations

    sentences expressing disappointment or critiques regarding understanding and actions taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skak
    -0.39
     jit
    -0.39
     מוס
    -0.36
    准
    -0.35
    んじゃない
    -0.35
     голо
    -0.35
    격
    -0.35
    kez
    -0.35
    ofür
    -0.35
     perspective
    -0.34
    POSITIVE LOGITS
     unfortunately
    3.72
     sadly
    3.31
    unfortunately
    3.30
    Unfortunately
    3.17
     Unfortunately
    3.13
     malheureusement
    3.03
     purtroppo
    3.00
    Sadly
    2.95
     Sadly
    2.94
     niestety
    2.92
    Activations Density 0.725%

    No Known Activations