© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4564
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance, necessity, or the importance of messages and viewpoints

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

    followed by prepositions or commas

    np_acts-logits-general · gemini-2.0-flash

    describing conditions or states

    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
     تانيه
    -1.14
    sidemargin
    -1.08
    Personendaten
    -0.96
    ConstraintMaker
    -0.93
     nakalista
    -0.86
     surla
    -0.85
     GIPHY
    -0.85
    findpost
    -0.84
    SharedCtor
    -0.83
    contentLoaded
    -0.83
    POSITIVE LOGITS
     a
    0.66
     M
    0.66
     Re
    0.63
     the
    0.63
     
    0.56
     in
    0.56
    ,
    0.56
     C
    0.55
     O
    0.55
     A
    0.55
    Activations Density 1.051%

    No Known Activations