© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5304
    Prev
    Next
    INDEX
    Explanations

    key plot elements related to space exploration and conflict

    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
     döne
    -0.34
     estrategia
    -0.34
     tarko
    -0.33
     estratégia
    -0.32
     utford
    -0.31
     leña
    -0.31
     ahorro
    -0.31
     lisäksi
    -0.30
     competencia
    -0.30
    PyErr
    -0.30
    POSITIVE LOGITS
     holog
    0.86
     hologram
    0.85
     holographic
    0.84
     implants
    0.81
     scanners
    0.79
     holo
    0.77
     cyber
    0.77
     decontamination
    0.76
     droid
    0.76
     containment
    0.73
    Activations Density 0.654%

    No Known Activations