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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9935
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming efficiency and optimization

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

    Preceding "to," "of," or "without."

    np_acts-logits-general · gemini-2.0-flash

    unnecessary without inconvenience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципалі
    -0.97
    出版年
    -0.96
    RegistryLite
    -0.93
     ExecuteAsync
    -0.92
     CreateTagHelper
    -0.91
    UrlResolution
    -0.89
    Portale
    -0.87
    DockStyle
    -0.86
     pinulongan
    -0.82
     Roskov
    -0.80
    POSITIVE LOGITS
     unnecessarily
    1.11
     needlessly
    1.07
     cumbersome
    1.06
     costly
    1.05
     unnecessary
    1.04
     expensive
    1.02
     tedious
    0.92
     wasteful
    0.90
    わざわざ
    0.89
     wasting
    0.85
    Activations Density 0.637%

    No Known Activations