© 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. 12529
    Prev
    Next
    INDEX
    Explanations

    HTML markup relevant to AngularJS components and directives

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

    Code or errors involving bracketed terms

    np_acts-logits-general · gemini-2.0-flash

    Standard must, corpus relief

    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
     '\\;'
    -0.77
    AndEndTag
    -0.70
     CreateTagHelper
    -0.64
    (@"%@",
    -0.62
     betweenstory
    -0.59
    
    -0.56
    richTextPanel
    -0.56
     <<<<<<<<<<<<<<
    -0.53
    Portail
    -0.53
    GEBURTSDATUM
    -0.53
    POSITIVE LOGITS
    ########.
    0.62
     QWidget
    0.56
    ercises
    0.52
    }{*}{}
    0.52
    ագրություններ
    0.52
    amaño
    0.51
     Hra
    0.51
     congru
    0.50
     isolado
    0.49
    ividual
    0.49
    Activations Density 0.014%

    No Known Activations