© 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
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2431
    Prev
    Next
    INDEX
    Explanations

    instances of specific character names or terms related to a fictional universe, particularly focusing on their roles or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.59
    InputBorder
    -0.58
     Photocase
    -0.56
     noDo
    -0.55
    yntaxException
    -0.55
    webElementXpaths
    -0.54
    Diweddarwch
    -0.53
     Autorizaciones
    -0.53
     snippetHide
    -0.52
    InjectAttribute
    -0.52
    POSITIVE LOGITS
     UIAlert
    0.42
    CppMethod
    0.37
    paddingVertical
    0.36
     ब्रेकडाउन
    0.35
     comuniques
    0.34
     Trail
    0.32
     dolo
    0.30
     Merdeka
    0.30
    Оп
    0.30
    ')}}">
    0.30
    Activations Density 1.884%

    No Known Activations