© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4998
    Prev
    Next
    INDEX
    Explanations

    references to the Bay Area

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

    "Bay" followed by a geographic term

    np_acts-logits-general · gemini-2.0-flash

    Bay Area

    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
    rungsseite
    -0.57
    はじめに
    -0.57
     OFDb
    -0.51
     klä
    -0.51
    rąg
    -0.51
    MessageTagHelper
    -0.50
    odacty
    -0.49
    WriteTagHelper
    -0.49
     CreateTagHelper
    -0.48
     khí
    -0.47
    POSITIVE LOGITS
    onets
    0.63
    PostInfinity
    0.60
    onet
    0.59
     Area
    0.57
     memoized
    0.55
    liss
    0.53
    +/**
    0.53
    RuleContext
    0.52
    angkan
    0.52
     الاطلاع
    0.51
    Activations Density 0.190%

    No Known Activations