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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 108732
    Prev
    Next
    INDEX
    Explanations

    references to young animals, particularly puppies and kittens

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

    puppy, kitten, rookie year

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ligiloj
    -0.63
    ="-
    -0.53
    asList
    -0.52
     "..\..\..\
    -0.50
     مرئيه
    -0.48
     يتيمه
    -0.48
    Portail
    -0.46
    ("|
    -0.46
    ↵↵↵↵↵
    -0.45
     '|
    -0.44
    POSITIVE LOGITS
     puppy
    1.91
     Puppy
    1.80
    Puppy
    1.73
    puppy
    1.58
     puppies
    1.49
     Puppies
    1.30
     kitten
    0.99
     Kitten
    0.79
     PUP
    0.79
     pup
    0.73
    Activations Density 0.004%

    No Known Activations