© 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. 23-GEMMASCOPE-RES-16K
    6. 8830
    Prev
    Next
    INDEX
    Explanations

    issues related to system reliability and potential for human error

    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
    нрави
    -0.34
    SupportActionBar
    -0.33
     przedstaw
    -0.32
     poži
    -0.31
     beat
    -0.31
    幸いです
    -0.31
     Heilig
    -0.31
    beat
    -0.30
     выход
    -0.30
    diel
    -0.30
    POSITIVE LOGITS
     prone
    0.82
     risks
    0.77
     risico
    0.77
     risk
    0.72
     risques
    0.72
     rischi
    0.68
     susceptible
    0.68
     dangers
    0.67
     risiko
    0.67
    execSQL
    0.66
    Activations Density 0.585%

    No Known Activations