© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 1051
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons and equality in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.63
    httphttps
    -0.58
     kasarigan
    -0.56
    HideFlags
    -0.54
    featureID
    -0.52
     насељу
    -0.52
    hoeddwyd
    -0.50
    JspWriter
    -0.49
    SequentialGroup
    -0.48
    ScopeManager
    -0.47
    POSITIVE LOGITS
     equal
    2.61
     Equal
    2.19
    equal
    2.19
     EQUAL
    2.14
     equality
    2.13
    Equal
    2.11
     equ
    2.08
     equals
    1.94
     égal
    1.91
    EQUAL
    1.88
    Activations Density 0.991%

    No Known Activations