Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10633
    Prev
    Next
    INDEX
    Explanations

    technical terms and abbreviations related to computer programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaiter
    -0.71
    Datuak
    -0.64
     виправивши
    -0.63
    __*/
    -0.61
    UserScript
    -0.61
     CascadeType
    -0.60
    NUMX
    -0.57
    outSlope
    -0.56
    HasForeignKey
    -0.56
    ioutil
    -0.56
    POSITIVE LOGITS
    ArrowToggle
    0.93
    AddTagHelper
    0.69
     betweenstory
    0.67
     ExecuteAsync
    0.66
     Rtl
    0.65
    featureID
    0.64
     AppCompatTheme
    0.59
     kasarigan
    0.58
    ViewFeatures
    0.57
    Geplaatst
    0.57
    Activations Density 1.580%

    No Known Activations