© 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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6710
    Prev
    Next
    INDEX
    Explanations

    references to a specific town or locality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archiviato
    -0.40
     protoimpl
    -0.39
    Tracce
    -0.38
    Genie
    -0.38
    Kaieteur
    -0.38
    licing
    -0.37
    erializer
    -0.36
    otropic
    -0.36
    gerichte
    -0.36
    ierre
    -0.36
    POSITIVE LOGITS
     town
    4.13
     Town
    3.47
    Town
    3.42
     TOWN
    3.30
    town
    3.11
     towns
    2.84
    TOWN
    2.81
    towns
    2.34
     Towns
    2.09
    Towns
    1.91
    Activations Density 0.060%

    No Known Activations