© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 20984
    Prev
    Next
    INDEX
    Explanations

    instances of the word "group" and its variations in conjunction with numbers or descriptors

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

    group of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maternidade
    -0.39
    ContentLoaded
    -0.39
     cielos
    -0.39
     kehamilan
    -0.39
     trasparente
    -0.38
     navideños
    -0.38
     secretos
    -0.38
     cosméticos
    -0.38
     deforestation
    -0.37
    "]));
    -0.37
    POSITIVE LOGITS
     group
    1.13
     GROUP
    0.98
    group
    0.96
     Gruppe
    0.96
     grup
    0.94
     groups
    0.93
    Gruppe
    0.92
     grupp
    0.92
    Group
    0.90
     GROUPS
    0.90
    Activations Density 0.029%

    No Known Activations