© 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. 15-GEMMASCOPE-RES-16K
    11. 12611
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing simplicity and ease of use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.74
    AndEndTag
    -0.72
    chromedriver
    -0.68
    bootstrapcdn
    -0.67
    contentLoaded
    -0.65
     joaat
    -0.65
    TagMode
    -0.64
     kasarigan
    -0.64
     NgModule
    -0.63
    Jeho
    -0.63
    POSITIVE LOGITS
    EASY
    1.24
     Easy
    1.23
    Easy
    1.21
     easy
    1.18
     EASY
    1.17
    easy
    1.09
     Easily
    1.06
     EAS
    1.05
     Eas
    0.99
     Easier
    0.99
    Activations Density 0.112%

    No Known Activations