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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10921
    Prev
    Next
    INDEX
    Explanations

    numeric values and their associations

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

    Numbers with hyphens

    np_acts-logits-general · gemini-2.0-flash

    citations and identifiers

    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
     
    -0.51
     Ben
    -0.51
     sur
    -0.42
     level
    -0.41
     all
    -0.41
     some
    -0.41
     out
    -0.41
    ada
    -0.41
     algum
    -0.41
    上一
    -0.41
    POSITIVE LOGITS
    NUMX
    0.98
    Referències
    0.83
     BoxFit
    0.82
    MigrationBuilder
    0.81
     itſelf
    0.80
    
    0.80
     photolibrary
    0.80
    windowFixed
    0.80
    GEBURTSDATUM
    0.78
     myſelf
    0.76
    Activations Density 0.579%

    No Known Activations