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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6534
    Prev
    Next
    INDEX
    Explanations

    instances of URLs, particularly those associated with GitHub repositories

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

    URLs to GitHub repositories

    np_acts-logits-general · gemini-2.0-flash

    github.com/ URLs

    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
    XtraReports
    -0.45
     
    -0.43
     AssemblyVersion
    -0.42
    wußt
    -0.42
     print
    -0.41
    jemah
    -0.41
    queryInterface
    -0.40
     مواليد
    -0.40
    __':
    -0.40
     –
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.71
    PyExc
    0.70
     Software
    0.67
    noons
    0.65
    tainers
    0.64
     itſelf
    0.64
    Software
    0.64
    software
    0.64
    êques
    0.63
     themſelves
    0.63
    Activations Density 0.304%

    No Known Activations