© 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. 27-GEMMASCOPE-RES-16K
    11. 9723
    Prev
    Next
    INDEX
    Explanations

    terms related to data analysis and comparison in scientific and socio-economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     praça
    -0.38
     nôtre
    -0.38
     automatique
    -0.38
    sidemargin
    -0.38
     işte
    -0.34
    ově
    -0.34
     piratas
    -0.34
    諳
    -0.34
     avulla
    -0.34
    úrg
    -0.33
    POSITIVE LOGITS
     receiver
    0.81
     receiving
    0.81
     recipient
    0.72
     Receiving
    0.69
     host
    0.66
    Receiving
    0.66
     Receiver
    0.65
    receiving
    0.65
    receiver
    0.65
     receivers
    0.63
    Activations Density 0.881%

    No Known Activations