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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15370
    Prev
    Next
    INDEX
    Explanations

    terms related to evaluation or judgment of quality and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    RegressionTest
    -0.62
    ఊ
    -0.56
     EconPapers
    -0.56
    IntoConstraints
    -0.55
     kiện
    -0.52
     and
    -0.51
    
    -0.51
    Theres
    -0.50
    НИК
    -0.50
     milliards
    -0.50
    POSITIVE LOGITS
    ?,?,
    0.60
    setVerticalGroup
    0.58
    }\]
    0.56
     therefore
    0.56
    Dtor
    0.56
    但也
    0.55
    sequently
    0.55
    ])),
    0.55
    tily
    0.54
    — 
    0.54
    Activations Density 0.663%

    No Known Activations