Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10717
    Prev
    Next
    INDEX
    Explanations

    terminology related to towing and vehicle coupling mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Vehicles and towing

    np_acts-logits-general · gemini-2.0-flash

    trailer and towing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.51
    ⎨
    -0.48
    Hentet
    -0.47
     InputDecoration
    -0.46
     esternos
    -0.45
     AssemblyVersion
    -0.45
    ngdoc
    -0.44
     CascadeType
    -0.43
    PCell
    -0.42
    oneph
    -0.42
    POSITIVE LOGITS
     trailer
    0.94
     Trailer
    0.87
    Trailer
    0.84
     trailers
    0.81
    trailer
    0.78
     towing
    0.77
     Trailers
    0.75
     Towing
    0.71
     tow
    0.70
     towed
    0.65
    Activations Density 0.176%

    No Known Activations