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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10832
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "never" and its various contexts, indicating a focus on denial or negation

    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
     متحده
    -0.65
    nesium
    -0.59
    bufio
    -0.57
    Pyx
    -0.57
     للمعارف
    -0.56
    setupUi
    -0.55
    horizontalLayout
    -0.55
     AOC
    -0.55
    omite
    -0.54
    AOC
    -0.54
    POSITIVE LOGITS
    never
    1.13
     never
    1.13
     NEVER
    1.10
    NEVER
    1.07
     Never
    1.07
    Never
    1.07
     ever
    0.98
     EVER
    0.94
    ever
    0.92
    Ever
    0.90
    Activations Density 0.126%

    No Known Activations