Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 454
    Prev
    Next
    INDEX
    Explanations

    expressions of sadness or negative emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cherichia
    -0.56
     dynamo
    -0.54
     Gouverneur
    -0.51
    FlatAppearance
    -0.49
     esternos
    -0.48
     muzzle
    -0.48
     StringTokenizer
    -0.46
    BuilderFactory
    -0.46
     Audiodateien
    -0.45
     spout
    -0.45
    POSITIVE LOGITS
     sedih
    0.73
     😢
    0.65
     sad
    0.65
     sadness
    0.64
     tristes
    0.63
     sorrow
    0.63
     Trauer
    0.63
     saddest
    0.63
     Sad
    0.63
     Sadler
    0.62
    Activations Density 0.285%

    No Known Activations