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. 16-GEMMASCOPE-RES-16K
    6. 12963
    Prev
    Next
    INDEX
    Explanations

    terms related to maximizing efficiency and effectiveness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    maximizing or benefits

    np_acts-logits-general · gemini-2.0-flash

    maximize exposure, efficiency, or benefit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +};
    -0.54
    ]]]
    -0.51
     Manns
    -0.47
    JspWriter
    -0.46
    >>();
    -0.46
    )))))
    -0.46
    kadang
    -0.45
    daging
    -0.45
     CreateTagHelper
    -0.44
    too
    -0.44
    POSITIVE LOGITS
     maximize
    1.31
     maximized
    1.24
     maximizing
    1.22
     maximise
    1.20
     Maximize
    1.15
     maximizes
    1.14
    maximize
    1.12
     maximum
    1.10
    Maximize
    1.06
     maximale
    1.06
    Activations Density 0.279%

    No Known Activations