© 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. 7365
    Prev
    Next
    INDEX
    Explanations

    references to various types and styles of bags and purses

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

    bags

    np_acts-logits-general · gemini-2.0-flash

    bags and pouches

    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
     kasarigan
    -0.39
    uktur
    -0.36
     dic
    -0.36
     dico
    -0.35
     dishon
    -0.34
     disc
    -0.33
    Ifc
    -0.33
    Malo
    -0.33
     déb
    -0.33
    endix
    -0.32
    POSITIVE LOGITS
     للمعارف
    0.68
     backpacks
    0.54
     Bags
    0.53
     handbags
    0.53
     يتيمه
    0.52
     bags
    0.50
     bolsos
    0.49
    municipi
    0.48
     Ausführungen
    0.48
    bags
    0.47
    Activations Density 0.090%

    No Known Activations