© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6941
    Prev
    Next
    INDEX
    Explanations

    references to dogs and their interactions, behaviors, and training

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

    "dog" or "dogs"

    np_acts-logits-general · gemini-2.0-flash

    dog behavior

    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
    ंदीखरीदारी
    -0.55
    揄
    -0.52
     cathédrale
    -0.52
    AndEndTag
    -0.51
    Chham
    -0.50
    
    -0.49
    Kaynakça
    -0.49
    乓
    -0.48
    ="{{$
    -0.48
    fxml
    -0.47
    POSITIVE LOGITS
     dog
    2.16
     dogs
    1.99
     Dog
    1.94
    Dog
    1.88
     Dogs
    1.88
    dog
    1.84
    Dogs
    1.74
     DOG
    1.73
    dogs
    1.73
     canine
    1.67
    Activations Density 0.205%

    No Known Activations