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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3212
    Prev
    Next
    INDEX
    Explanations

    mentions of libraries and related institutions

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

    "library"

    np_acts-logits-general · gemini-2.0-flash

    library

    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
     Jesus
    -0.41
     risky
    -0.41
     Runnable
    -0.40
     Forza
    -0.40
     danger
    -0.40
     God
    -0.39
     Venture
    -0.39
     Viti
    -0.38
     Damon
    -0.38
    RectangleBorder
    -0.38
    POSITIVE LOGITS
     library
    2.11
     Library
    2.05
    Library
    2.03
    library
    1.98
     LIBRARY
    1.74
     biblioteca
    1.70
     libraries
    1.68
     bibliothèque
    1.66
     Libraries
    1.65
    LIBRARY
    1.65
    Activations Density 0.095%

    No Known Activations