© 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. 22-GEMMASCOPE-RES-16K
    6. 9457
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and landmarks

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

    Follows prepositions like "from", "of", and "in"

    np_acts-logits-general · gemini-2.0-flash

    locations following prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     huelga
    -0.47
     Administrativna
    -0.47
     >=",
    -0.47
    Fuckin
    -0.46
     DbSet
    -0.45
     rectifier
    -0.45
    ñó
    -0.44
    StackNavigator
    -0.43
     häls
    -0.43
    ILayout
    -0.43
    POSITIVE LOGITS
    endphp
    0.63
     Scars
    0.62
    󠁣
    0.61
     affluent
    0.60
     estekak
    0.57
    âce
    0.57
    rąg
    0.56
    InputTagHelper
    0.56
     CWE
    0.56
    Хьажоргаш
    0.54
    Activations Density 0.173%

    No Known Activations