© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10594
    Prev
    Next
    INDEX
    Explanations

    terms related to cooperative or collaborative efforts, especially in research contexts

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

    "co" prefix or "co-workers"

    np_acts-logits-general · gemini-2.0-flash

    co followed by hyphen or period

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    GenerationType
    -0.48
    marvin
    -0.45
    jerc
    -0.43
    felizmente
    -0.43
     Blumen
    -0.42
    zard
    -0.41
    theless
    -0.41
    currentPage
    -0.41
     ABSOL
    -0.41
     Jär
    -0.41
    POSITIVE LOGITS
     co
    1.89
    Co
    1.89
     Co
    1.88
    co
    1.59
    CO
    1.31
     CO
    1.25
    CoA
    0.94
     cobalt
    0.94
    Cof
    0.91
     covariates
    0.88
    Activations Density 0.176%

    No Known Activations