© 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. 4199
    Prev
    Next
    INDEX
    Explanations

    specific patterns of numeric data and punctuation related to responses or code structures

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

    HTTP response codes

    np_acts-logits-general · gemini-2.0-flash

    statistical significance

    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
     resourceCulture
    -0.93
    IndentedString
    -0.90
     nahilalakip
    -0.89
    RenderAtEndOf
    -0.86
    RegistryLite
    -0.86
    bootstrapcdn
    -0.84
     Efq
    -0.83
    CodedInputStream
    -0.78
    StoryboardSegue
    -0.77
    Décès
    -0.76
    POSITIVE LOGITS
    0
    0.58
    1
    0.53
    AxisAlignment
    0.50
    3
    0.48
    2
    0.45
    ––––
    0.45
    mitives
    0.42
    4
    0.41
     Sal
    0.41
     Tra
    0.41
    Activations Density 0.146%

    No Known Activations