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

    Neuronpedia

    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. 23-GEMMASCOPE-RES-16K
    11. 8447
    Prev
    Next
    INDEX
    Explanations

    HTML or XML class attributes in code segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.63
    JspWriter
    -0.61
    stateProvider
    -0.60
     Roskov
    -0.58
    ngOnInit
    -0.58
     الرخصة
    -0.57
    routeProvider
    -0.55
    MessageTagHelper
    -0.54
    MessageDigest
    -0.52
     mapStateToProps
    -0.52
    POSITIVE LOGITS
     colspan
    1.16
     rowspan
    0.88
    enumi
    0.87
    enumii
    0.69
    出版年
    0.65
     pinulongan
    0.63
     محفوظة
    0.58
    󠁮
    0.58
    CompilerServices
    0.57
     ſame
    0.56
    Activations Density 0.087%

    No Known Activations