© 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. 18-GEMMASCOPE-RES-16K
    11. 10911
    Prev
    Next
    INDEX
    Explanations

    phrases indicating awareness or recognition of people, brands, or concepts that the audience may not be familiar with

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

    Follows "will" or indicates something not commonly known

    np_acts-logits-general · gemini-2.0-flash

    knowing or not knowing someone/something

    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
    CascadeType
    -0.47
    tonsoft
    -0.47
    }\{
    -0.46
    antMatchers
    -0.45
    جوايز
    -0.45
    currentThread
    -0.44
    warzys
    -0.44
    énieurs
    -0.43
    MES
    -0.43
     mergeFrom
    -0.41
    POSITIVE LOGITS
     familiarity
    1.28
     unfamiliar
    1.27
     desconoc
    1.22
     acquaintance
    1.20
     familiar
    1.20
     Familiar
    1.17
     conosci
    1.15
    familiar
    1.14
     Unknown
    1.11
     unknown
    1.11
    Activations Density 0.277%

    No Known Activations