© 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. 36-GEMMASCOPE-RES-16K
    11. 13651
    Prev
    Next
    INDEX
    Explanations

    actions and activities related to movement and interaction

    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
    spesies
    -0.55
    ⟬
    -0.50
    новништво
    -0.49
     trám
    -0.49
    AutoField
    -0.48
    Personendaten
    -0.48
     circulating
    -0.48
    一部分
    -0.47
     umgangssprach
    -0.46
     slipping
    -0.44
    POSITIVE LOGITS
     away
    0.68
     madly
    0.68
     merrily
    0.59
     furiously
    0.59
     wildly
    0.56
     incessantly
    0.53
     frantically
    0.53
     endlessly
    0.50
     AWAY
    0.50
    Away
    0.49
    Activations Density 0.379%

    No Known Activations