© 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. 9858
    Prev
    Next
    INDEX
    Explanations

    descriptions related to pathways and natural settings

    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
     defaultstate
    -0.47
     vrijwilli
    -0.43
    Datuak
    -0.42
    MemoryWarning
    -0.40
    tidy
    -0.40
    riwal
    -0.40
    rungsseite
    -0.40
    vaux
    -0.39
    arakhand
    -0.38
     désolés
    -0.38
    POSITIVE LOGITS
     approaching
    0.62
     nearing
    0.57
     arrive
    0.56
    arriver
    0.56
     entering
    0.55
     arrival
    0.53
     arrives
    0.52
     enters
    0.52
     arrived
    0.51
     memasuki
    0.49
    Activations Density 0.227%

    No Known Activations