© 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. 28-GEMMASCOPE-RES-16K
    11. 7967
    Prev
    Next
    INDEX
    Explanations

    administrative terms related to organizational identity and contact information

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

    Street addresses or locations

    np_acts-logits-general · gemini-2.0-flash

    address or location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Aktualisiert
    -0.57
    سطس
    -0.47
    IsPostBack
    -0.46
    ResumeLayout
    -0.46
     lievito
    -0.45
    phosa
    -0.44
    әрмәләр
    -0.44
    Referanser
    -0.44
    <?
    -0.44
    GenerationType
    -0.43
    POSITIVE LOGITS
     address
    0.95
     Address
    0.93
    Address
    0.87
    address
    0.79
     ADDRESS
    0.77
    ADDRESS
    0.72
    地址
    0.69
     addressed
    0.66
     addresses
    0.66
     located
    0.65
    Activations Density 0.172%

    No Known Activations