© 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. 36-GEMMASCOPE-RES-16K
    11. 11364
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities in both legal and casual contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.73
    forRoot
    -0.49
    RepeatedField
    -0.47
    孩子们
    -0.46
    دانشنامهٔ
    -0.45
     initComponents
    -0.44
    AndEndTag
    -0.43
     nahilalakip
    -0.43
     Taktlose
    -0.42
    LabelTagHelper
    -0.42
    POSITIVE LOGITS
     person
    3.23
     Person
    2.66
    person
    2.66
     persons
    2.66
    Person
    2.55
     PERSON
    2.48
     Persons
    2.27
    persons
    2.22
    Persons
    2.20
    PERSON
    2.19
    Activations Density 0.476%

    No Known Activations