Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 24212
    Prev
    Next
    INDEX
    Explanations

    terms related to relay systems and their functions

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

    relay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.52
    Damien
    -0.41
    Cleveland
    -0.41
     Gucci
    -0.40
     Schwarzenegger
    -0.40
     botto
    -0.40
    Dustin
    -0.38
     byste
    -0.37
    Gucci
    -0.37
    Darth
    -0.37
    POSITIVE LOGITS
     relay
    2.45
     Relay
    2.30
    relay
    2.23
    Relay
    2.20
     relays
    2.08
     relayed
    1.59
     relais
    1.34
     REL
    1.04
     Rel
    1.03
     Rela
    0.90
    Activations Density 0.004%

    No Known Activations