© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1724
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to programming and mathematical expressions

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

    Code snippets with brackets, parentheses, or equals signs

    np_acts-logits-general · gemini-2.0-flash

    equation structure or programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.50
     henvisninger
    -0.45
     respectivamente
    -0.45
    tembro
    -0.45
    [toxicity=0]
    -0.44
    </i>
    -0.43
    ↵
    -0.43
     Einwohner
    -0.42
    
    -0.42
    MENAFN
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.96
     BoxFit
    0.90
    djangoproject
    0.85
    ὖ
    0.74
    exitRule
    0.71
     Signalez
    0.71
    AndroidJUnit
    0.71
    SizeF
    0.71
    -------------</
    0.70
    PostConstruct
    0.70
    Activations Density 1.399%

    No Known Activations