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. 122400
    Prev
    Next
    INDEX
    Explanations

    references to academic assessments and evaluation processes

    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
     OnTrigger
    -0.40
     lý
    -0.40
    Slf
    -0.38
     Table
    -0.37
     lineup
    -0.37
     ویکی‌پدیای
    -0.36
     đôi
    -0.36
    Rück
    -0.35
     termo
    -0.35
     experiments
    -0.35
    POSITIVE LOGITS
    Tracce
    0.50
    Билгалдахарш
    0.48
     Constitucional
    0.47
    pecabe
    0.47
     estudar
    0.44
    ➟
    0.43
    受験
    0.43
    CppMethod
    0.42
     tombé
    0.41
     ansiedad
    0.41
    Activations Density 0.051%

    No Known Activations