© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10249
    Prev
    Next
    INDEX
    Explanations

    instances of the word "never" and its various contexts in relation to past experiences

    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
     للمعارف
    -0.67
    bufio
    -0.63
     OMITTED
    -0.60
     متحده
    -0.59
    Pyx
    -0.59
    حياته
    -0.59
    SizeMode
    -0.58
    omite
    -0.56
     Enix
    -0.56
    formatics
    -0.54
    POSITIVE LOGITS
    never
    0.97
     never
    0.94
     NEVER
    0.92
    NEVER
    0.91
    Never
    0.91
     Never
    0.90
     ever
    0.84
    ever
    0.82
     EVER
    0.82
    Ever
    0.80
    Activations Density 0.107%

    No Known Activations