© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16073
    Prev
    Next
    INDEX
    Explanations

    prominent news organizations and television broadcasting terms

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

    news and broadcast television programming references.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.35
     láp
    -0.33
     יִ
    -0.32
     koul
    -0.31
    itinéraire
    -0.30
     térmico
    -0.30
    nps
    -0.30
     vuoden
    -0.29
     Lyft
    -0.28
     emprender
    -0.28
    POSITIVE LOGITS
     broadcast
    1.94
     television
    1.92
     broadcasting
    1.80
     TV
    1.79
     broadcasts
    1.76
     televis
    1.75
     Television
    1.73
     broadcasters
    1.70
     tv
    1.66
    Television
    1.63
    Activations Density 0.704%

    No Known Activations