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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 9496
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical or mathematical representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.94
    OGND
    -0.85
    EndGlobalSection
    -0.83
    يكب
    -0.81
    تقاوى
    -0.78
    TintMode
    -0.76
    曖昧さ回避
    -0.73
     كومونز
    -0.72
    -------------</
    -0.70
     فريبيس
    -0.70
    POSITIVE LOGITS
     []:
    0.56
     ""))
    0.55
     "");
    
    0.52
     $\
    0.47
    DebuggerStep
    0.46
    ()?;
    0.45
    PDOException
    0.44
     S
    0.43
    )=>{
    
    0.42
    jà
    0.41
    Activations Density 0.085%

    No Known Activations