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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67581
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific programming function declarations and comments

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     queſta
    -1.09
    niſſe
    -1.03
    ſicht
    -1.02
    ſſung
    -1.00
    ſchaft
    -0.98
     protoimpl
    -0.97
    iſchen
    -0.96
     utafitiHapana
    -0.95
     Infórmanos
    -0.95
    <unused41>
    -0.94
    POSITIVE LOGITS
    1
    0.51
    The
    0.47
    0
    0.46
    import
    0.46
    In
    0.45
    _
    0.44
    2
    0.44
    I
    0.41
    ,
    0.40
    ↵↵
    0.39
    Activations Density 0.013%

    No Known Activations