© 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. 5-GEMMASCOPE-RES-16K
    11. 6057
    Prev
    Next
    INDEX
    Explanations

    programming elements and structures related to UI component layout and functionality in build environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.89
    CloseOperation
    -0.84
    ArgsConstructor
    -0.80
    jsonwebtoken
    -0.76
    الحياه
    -0.74
    存于互联网档案馆
    -0.72
     BoxDecoration
    -0.71
    yargs
    -0.67
    XmlAccessType
    -0.66
    globin
    -0.66
    POSITIVE LOGITS
    HtmlAttribute
    1.30
    /***/
    0.94
     @"/
    0.89
    IsContent
    0.76
    LayoutInflater
    0.70
    rxjs
    0.69
    XMLSchema
    0.58
    offsetof
    0.53
    JspWriter
    0.52
     uitgenodigd
    0.51
    Activations Density 0.020%

    No Known Activations