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. 128982
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "console."

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

    javascript console.log

    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
    สิน
    -0.43
     tiens
    -0.43
     Artist
    -0.42
    팎
    -0.41
     Raff
    -0.41
     Outros
    -0.41
     rangs
    -0.40
    dentist
    -0.40
     aident
    -0.40
     てる
    -0.40
    POSITIVE LOGITS
    console
    2.34
     console
    1.09
    Console
    1.05
    printStackTrace
    1.05
    CONSOLE
    0.87
     Console
    0.85
    Println
    0.69
     consoles
    0.69
    npmjs
    0.69
    stdio
    0.68
    Activations Density 0.004%

    No Known Activations