© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1754
    Prev
    Next
    INDEX
    Explanations

    features related to battery-saving settings and options in applications

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

    Follows punctuation or "you"

    np_acts-logits-general · gemini-2.0-flash

    delete files

    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
    BeginContext
    -0.69
    ArgsConstructor
    -0.68
     ModelExpression
    -0.63
    twimg
    -0.60
    tagext
    -0.60
    期刊论文
    -0.60
    styleUrls
    -0.58
    SpringRunner
    -0.55
    nessed
    -0.55
    MOQ
    -0.55
    POSITIVE LOGITS
     settings
    0.67
     Settings
    0.65
     privacy
    0.61
     Windows
    0.61
     annoying
    0.61
     apps
    0.60
     activation
    0.60
     software
    0.59
     browser
    0.59
     manually
    0.59
    Activations Density 0.510%

    No Known Activations