© 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. 18-GEMMASCOPE-RES-16K
    11. 8859
    Prev
    Next
    INDEX
    Explanations

    affordable luxury products and services

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

    affordability or low cost

    np_acts-logits-general · gemini-2.0-flash

    cheap, affordable, inexpensive prices

    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
    ❋
    -0.54
     оригіналу
    -0.54
    moveToFirst
    -0.54
    __*/
    -0.52
    ########.
    -0.48
     {?}
    -0.47
    BindView
    -0.46
    createServer
    -0.45
     sfer
    -0.45
     Zier
    -0.44
    POSITIVE LOGITS
     cheap
    2.15
     cheaper
    2.07
     inexpensive
    1.85
     cheapest
    1.83
    cheap
    1.83
     cheaply
    1.78
     affordable
    1.77
     Cheaper
    1.71
    Cheap
    1.68
     Cheap
    1.67
    Activations Density 0.169%

    No Known Activations