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. 795
    Prev
    Next
    INDEX
    Explanations

    references to the AppCompat library in Android programming

    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
     AttributeSet
    -0.70
    cokinetics
    -0.62
    ergies
    -0.60
    Getenv
    -0.59
    GEBURTS
    -0.59
     دریافت‌شده
    -0.58
    кви
    -0.57
     typename
    -0.55
     rehearing
    -0.55
    Harm
    -0.55
    POSITIVE LOGITS
    tagHelper
    1.73
    enumi
    1.14
    AutoSize
    1.07
    IsContent
    0.91
    AddHtmlAttribute
    0.80
    twimg
    0.78
    commons
    0.78
    InsertCommand
    0.74
    tagHelperRunner
    0.73
     initComponents
    0.72
    Activations Density 0.027%

    No Known Activations