© 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. 36-GEMMASCOPE-RES-16K
    11. 16011
    Prev
    Next
    INDEX
    Explanations

    the word "Bangsar" and its variations related to locations or context involving Bangsar

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.59
    ThemeOverlay
    -0.43
     noDo
    -0.43
    +#+
    -0.41
    setVerticalGroup
    -0.41
     transférez
    -0.40
     Waray
    -0.40
     ModelRenderer
    -0.39
    PreInfinity
    -0.38
     للاسماء
    -0.37
    POSITIVE LOGITS
    gggg
    0.63
    ค์
    0.58
    ggg
    0.56
    ang
    0.50
    ANG
    0.49
    tang
    0.48
    gar
    0.48
    gg
    0.48
     wireType
    0.47
     TANG
    0.46
    Activations Density 0.158%

    No Known Activations