© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1915
    Prev
    Next
    INDEX
    Explanations

    specific entities related to biological, ecological, or technological elements

    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
    writeFieldEnd
    -0.81
    basicConfig
    -0.79
    webElementXpaths
    -0.71
    ContentAsync
    -0.64
    ThroughAttribute
    -0.63
    Personensuche
    -0.63
    tagHelperRunner
    -0.62
    UnusedPrivate
    -0.62
    "],
    
    -0.60
    ")){
    
    -0.60
    POSITIVE LOGITS
    Off
    0.59
     Off
    0.55
    off
    0.51
     pinulongan
    0.50
     off
    0.46
     alpes
    0.45
     UIImageView
    0.44
    Parameterized
    0.44
     Pleas
    0.43
    OFF
    0.43
    Activations Density 0.922%

    No Known Activations