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

    Neuronpedia

    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. 37-GEMMASCOPE-RES-16K
    11. 3516
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions or desires, often involving the verb "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     همچنین
    -0.35
     appunto
    -0.35
     notably
    -0.33
     insbesondere
    -0.33
    autaire
    -0.30
     précisément
    -0.29
     kako
    -0.29
    |()
    -0.29
    Geografía
    -0.29
     earlier
    -0.29
    POSITIVE LOGITS
     learns
    0.72
     forgets
    0.72
     disappear
    0.72
     disappears
    0.70
     discovers
    0.67
     teaches
    0.66
    pecabe
    0.66
     receives
    0.66
     achieves
    0.66
     survived
    0.65
    Activations Density 2.365%

    No Known Activations