© 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 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. 15558
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain significant semantic content or commentary

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

    Code, programming languages, or data formats

    np_acts-logits-general · gemini-2.0-flash

    programming code snippets

    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
     Wyman
    -0.58
    kloped
    -0.58
    CLUYE
    -0.54
    rangian
    -0.52
    Lịch
    -0.51
    estión
    -0.51
    adeira
    -0.50
     isInitialized
    -0.49
    igshid
    -0.49
    poietic
    -0.48
    POSITIVE LOGITS
    String
    0.68
     String
    0.62
     createSprite
    0.61
     AssemblyTitle
    0.59
     strdup
    0.54
    awakeFromNib
    0.53
     &___
    0.52
    string
    0.52
    sune
    0.49
    getStringExtra
    0.49
    Activations Density 0.047%

    No Known Activations