© 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. 17-GEMMASCOPE-RES-16K
    6. 4846
    Prev
    Next
    INDEX
    Explanations

    specific mathematical expressions and symbols in the context of statistical modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '%'
    -0.46
     cucchiaio
    -0.44
    }}/>
    -0.43
    ikir
    -0.42
    ('');
    -0.42
     PrintWriter
    -0.42
     []
    
    -0.42
     التح
    -0.42
    ']='
    -0.41
     sw
    -0.41
    POSITIVE LOGITS
    లాలు
    0.70
     EconPapers
    0.69
     random
    0.66
     мәкал
    0.66
     useAppContext
    0.63
     propOrder
    0.63
    AnchorStyles
    0.63
    WriteTagHelper
    0.62
     randomly
    0.62
     crdi
    0.61
    Activations Density 1.985%

    No Known Activations