© 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. 12643
    Prev
    Next
    INDEX
    Explanations

    code syntax and structural elements related to programming

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

    Code snippets/blocks

    np_acts-logits-general · gemini-2.0-flash

    code terminating characters

    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
     Normdatei
    -0.84
     NSCoder
    -0.77
    tonode
    -0.77
    webElementXpaths
    -0.76
    tanleria
    -0.74
     BorderRadius
    -0.73
    jspb
    -0.73
     endforeach
    -0.72
    endpush
    -0.71
    MessageTagHelper
    -0.71
    POSITIVE LOGITS
     hår
    0.51
     elettron
    0.49
     umana
    0.49
     popolari
    0.49
    ivo
    0.48
    uch
    0.47
     cheminée
    0.47
     sentimientos
    0.47
     termica
    0.46
    ModelAndView
    0.46
    Activations Density 0.674%

    No Known Activations