© 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. 16-GEMMASCOPE-RES-16K
    6. 4782
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax related to JavaScript imports and component creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code syntax: curly braces and parentheses

    np_acts-logits-general · gemini-2.0-flash

    create navigation components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.77
     AttributeSet
    -0.72
    sendFile
    -0.71
    OpenHelper
    -0.67
     lenker
    -0.67
     TabLayout
    -0.65
    gettime
    -0.63
     onPostExecute
    -0.63
    afficheront
    -0.62
    jsonwebtoken
    -0.62
    POSITIVE LOGITS
    "])){
    0.54
    ={({
    0.54
    "){
    
    0.52
    ,:),
    0.52
    "])
    
    0.51
     )}$
    0.50
     }
    0.48
    ajs
    0.48
    "},
    
    0.47
    ักษ
    0.47
    Activations Density 0.012%

    No Known Activations