© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7714
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to squares and square shapes

    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
    жер
    -0.28
    a
    -0.28
    부
    -0.28
    ://
    -0.28
    switch
    -0.28
     actual
    -0.27
    Ben
    -0.27
     Kett
    -0.27
    underset
    -0.27
    original
    -0.27
    POSITIVE LOGITS
     Enix
    0.94
     HasFactory
    0.82
    хьтан
    0.75
     '\\;'
    0.71
     squa
    0.68
     Sq
    0.66
    +#+#
    0.65
     SQ
    0.65
     SQU
    0.64
     SQUARE
    0.64
    Activations Density 0.246%

    No Known Activations