© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4266
    Prev
    Next
    INDEX
    Explanations

    code elements and programming constructs

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

    Code, filenames, or paths ending in specific extensions

    np_acts-logits-general · gemini-2.0-flash

    -ing words and phrases

    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
     defStyleAttr
    -0.53
     مشين
    -0.51
    .~(\
    -0.51
    backpack
    -0.49
    rowave
    -0.49
     parachute
    -0.48
    ,"%
    -0.48
    Climb
    -0.48
    ंदीखरीदारी
    -0.48
     endforeach
    -0.48
    POSITIVE LOGITS
    ning
    0.88
    ding
    0.84
    baking
    0.83
    ing
    0.82
     ing
    0.81
    inting
    0.80
     baking
    0.79
    ADING
    0.78
    singing
    0.78
    ings
    0.78
    Activations Density 0.375%

    No Known Activations