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
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7826
    Prev
    Next
    INDEX
    Explanations

    references to dog behavior or training-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.46
    rrggbb
    -0.45
    ByVersion
    -0.45
    تقاوى
    -0.43
    LEncoder
    -0.42
    TypedDataSet
    -0.42
    icitis
    -0.38
    audiovisuel
    -0.38
     nonUne
    -0.38
    Erstellt
    -0.37
    POSITIVE LOGITS
     dog
    2.95
     dogs
    2.86
     Dogs
    2.50
     Dog
    2.44
    Dogs
    2.39
    Dog
    2.38
    dog
    2.34
     canine
    2.33
    dogs
    2.27
     DOG
    2.20
    Activations Density 0.375%

    No Known Activations