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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 15748
    Prev
    Next
    INDEX
    Explanations

    the beginning of code comments and license information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -1.02
    InjectAttribute
    -0.92
    хьтан
    -0.88
     ModelExpression
    -0.86
    pecabe
    -0.83
     arşivlendi
    -0.83
     Geſch
    -0.82
    ésultats
    -0.82
     queſta
    -0.82
    ロウィン
    -0.79
    POSITIVE LOGITS
    /*
    0.43
     <<<<<<<<<<<<<<
    0.39
    ↵
    0.32
    """
    0.32
    ("""
    0.31
    :
    0.31
    _
    0.30
    Function
    0.30
    0
    0.30
    1
    0.30
    Activations Density 0.159%

    No Known Activations