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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 1071
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons and greater-than symbols in numerical contexts

    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
    ation
    -0.64
    '
    -0.60
    son
    -0.60
     stress
    -0.56
    jal
    -0.54
    XtraGrid
    -0.53
     Ball
    -0.52
    sona
    -0.51
    лю
    -0.50
    istani
    -0.50
    POSITIVE LOGITS
    >>>>>>>>
    1.42
    displayquote
    1.31
    >>>>
    1.27
    >>>>>>
    1.23
    >>>>>>>
    1.22
    }>\
    1.16
     $>$
    1.15
    >>>
    1.14
    SpringBootTest
    1.13
    >\
    1.10
    Activations Density 0.220%

    No Known Activations