© 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. 5-GEMMASCOPE-RES-16K
    11. 10649
    Prev
    Next
    INDEX
    Explanations

    repetition patterns or sequences in data

    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
    .
    -0.72
    webElementXpaths
    -0.67
    </i>
    -0.46
    ?
    -0.45
    ↵
    -0.45
    l
    -0.45
    BeanFactory
    -0.44
     (
    -0.44
    -
    -0.42
     {
    -0.42
    POSITIVE LOGITS
    +#+
    1.24
    RetentionPolicy
    1.05
     CreateTagHelper
    0.99
    tagHelperRunner
    0.98
     itſelf
    0.97
    OGND
    0.96
     Efq
    0.90
    énario
    0.87
     houſe
    0.85
     myſelf
    0.85
    Activations Density 0.281%

    No Known Activations