© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9912
    Prev
    Next
    INDEX
    Explanations

    concepts related to collective actions and unity

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

    "collective" or its variations

    np_acts-logits-general · gemini-2.0-flash

    collective determination, destiny

    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
     Investigaciones
    -0.28
    zubauen
    -0.28
    quién
    -0.28
    "}")
    -0.28
    щадь
    -0.28
    "]),
    -0.27
    "]);
    
    -0.27
     ""),
    -0.26
     "").
    -0.26
    "]));
    -0.25
    POSITIVE LOGITS
     collective
    1.54
    collective
    1.52
    Collective
    1.50
     collectively
    1.39
     Collective
    1.32
    集体
    1.20
     kollek
    1.16
     collectif
    1.10
     colectiva
    1.07
     colectivo
    0.93
    Activations Density 0.402%

    No Known Activations