© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9462
    Prev
    Next
    INDEX
    Explanations

    terms related to escalating levels or increases in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flav
    -0.53
     BorderRadius
    -0.52
    assertj
    -0.51
     CONT
    -0.51
     PUBL
    -0.50
     StringTokenizer
    -0.48
    contentPadding
    -0.48
    Flav
    -0.48
    assertIs
    -0.47
     Payload
    -0.47
    POSITIVE LOGITS
     increase
    0.89
    Increase
    0.89
     Increase
    0.88
    increase
    0.82
     INCREASE
    0.73
    decrease
    0.73
     increased
    0.71
     zvý
    0.71
     Erhöhung
    0.70
    Decrease
    0.69
    Activations Density 0.299%

    No Known Activations