© 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 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. 15282
    Prev
    Next
    INDEX
    Explanations

    repetitive conjunctions and phrases indicating contrast or comparison

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

    "as" or "so" followed by "is/are/has/have/will"

    np_acts-logits-general · gemini-2.0-flash

    as well as, so does

    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
    WriteTagHelper
    -0.64
    TypedDataSet
    -0.62
     rood
    -0.60
     purpoſe
    -0.54
    ftagPool
    -0.53
     Offisielt
    -0.53
    Související
    -0.50
    τεύ
    -0.50
    irsten
    -0.50
     Dider
    -0.50
    POSITIVE LOGITS
     does
    1.07
     did
    0.98
     do
    0.81
     Does
    0.81
    Does
    0.74
     were
    0.73
    did
    0.72
     are
    0.69
    does
    0.69
    Did
    0.68
    Activations Density 0.150%

    No Known Activations