© 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. 14658
    Prev
    Next
    INDEX
    Explanations

    phrases related to television programming and network structures

    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
    AnchorStyles
    -0.27
    cijos
    -0.27
    endwhile
    -0.26
    дження
    -0.26
     pistas
    -0.26
    สอบ
    -0.25
    ̀u
    -0.25
    usermodel
    -0.25
     láp
    -0.24
    trauer
    -0.24
    POSITIVE LOGITS
     broadcast
    2.41
     television
    2.38
     broadcasting
    2.27
     TV
    2.22
     Television
    2.16
     televis
    2.16
     broadcasters
    2.13
     broadcasts
    2.08
     Broadcast
    2.06
     tv
    2.05
    Activations Density 0.962%

    No Known Activations