© 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. 6553
    Prev
    Next
    INDEX
    Explanations

    geographical and infrastructural terms related to roads and pathways

    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
    Sample
    -0.35
    classmethod
    -0.35
     хозяй
    -0.35
     getattr
    -0.32
     样
    -0.30
     pilota
    -0.30
     Sample
    -0.30
     سرم
    -0.29
     pla
    -0.29
    们
    -0.29
    POSITIVE LOGITS
     Road
    1.90
     Avenue
    1.77
     Rd
    1.52
    Avenue
    1.51
     Street
    1.47
    Road
    1.47
     AVENUE
    1.44
     Ave
    1.41
     Boulevard
    1.41
     Blvd
    1.20
    Activations Density 0.511%

    No Known Activations