© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1861
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hubiese
    -0.41
     sanitarias
    -0.40
     Añade
    -0.40
     있어
    -0.40
     nhất
    -0.39
     apprécier
    -0.39
     مباشرة
    -0.39
    UnusedPrivate
    -0.39
    ambilan
    -0.39
     orejas
    -0.37
    POSITIVE LOGITS
    脚注の使い方
    0.52
     AssemblyCompany
    0.50
     versus
    0.48
     fá
    0.45
     utafitiHapana
    0.44
     AssemblyVersion
    0.44
    UIControlState
    0.44
     ویکی‌پدیای
    0.43
    CLIN
    0.42
    getOr
    0.42
    Activations Density 0.264%

    No Known Activations