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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 11253
    Prev
    Next
    INDEX
    Explanations

    instances of conditional or subjective statements

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

    followed by contractions or the word "is"

    np_acts-logits-general · gemini-2.0-flash

    concessionary introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Either
    -0.96
     Either
    -0.90
    更是
    -0.86
     even
    -0.85
     invece
    -0.84
    either
    -0.82
     either
    -0.82
     malah
    -0.81
    even
    -0.79
     instead
    -0.78
    POSITIVE LOGITS
     technically
    1.37
     nominally
    1.30
     initially
    1.25
     outwardly
    1.14
     ostensibly
    1.13
     superfic
    1.11
     admittedly
    1.08
     theoretically
    1.03
     inicialmente
    1.02
     téc
    0.98
    Activations Density 0.444%

    No Known Activations