© 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. 41-GEMMASCOPE-RES-16K
    6. 10596
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional vulnerability and desire for connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Poop
    -0.64
     poop
    -0.53
    poop
    -0.52
    WithIOException
    -0.50
    Fart
    -0.50
    期刊论文
    -0.47
     Granny
    -0.46
    Fluffy
    -0.44
     Aunt
    -0.43
    afficheront
    -0.43
    POSITIVE LOGITS
     {?}
    0.60
     
    0.48
    LLocation
    0.47
     masquerade
    0.47
     
    0.46
     neón
    0.45
     broken
    0.43
     fading
    0.42
     [?]
    0.41
    DockStyle
    0.40
    Activations Density 0.254%

    No Known Activations