© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10923
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal structures and inequalities

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

    "Local" or mentions of local places

    np_acts-logits-general · gemini-2.0-flash

    local and locals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"/
    -0.44
    ARROLL
    -0.42
    AsUp
    -0.39
    DockStyle
    -0.35
     sveta
    -0.35
    CloseOperation
    -0.34
    unknownFields
    -0.33
    Exterior
    -0.33
     faudra
    -0.33
    rientes
    -0.32
    POSITIVE LOGITS
     local
    2.72
     locally
    2.55
    local
    2.36
     LOCAL
    2.14
     locals
    2.14
    Local
    2.13
     Locally
    2.13
    locally
    2.11
     Local
    2.09
     lokal
    2.08
    Activations Density 0.823%

    No Known Activations