© 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. 951
    Prev
    Next
    INDEX
    Explanations

    references to errors or mistakes in various contexts

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

    Typos and errors

    np_acts-logits-general · gemini-2.0-flash

    errors and typos

    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
    complexContent
    -0.63
     BitmapFactory
    -0.51
    nologie
    -0.50
    IUrlHelper
    -0.49
    PerformLayout
    -0.49
    rils
    -0.48
    ędziesz
    -0.48
     '>=
    -0.47
     متعلقه
    -0.46
    UrlResolution
    -0.46
    POSITIVE LOGITS
     mistakes
    2.14
     errors
    2.01
     Mistakes
    1.86
     error
    1.85
     Errors
    1.79
     mistake
    1.71
     errores
    1.62
     erreurs
    1.62
    errors
    1.59
    Errors
    1.59
    Activations Density 0.458%

    No Known Activations