© 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
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1545
    Prev
    Next
    INDEX
    Explanations

    specific programming commands or keywords related to structure definitions in code

    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
    CppMethod
    -0.40
    MethodManager
    -0.31
    音を
    -0.28
    した場合
    -0.28
     str
    -0.27
     exten
    -0.27
     models
    -0.26
     options
    -0.25
     Stro
    -0.23
    PrototypeOf
    -0.23
    POSITIVE LOGITS
     صوتيه
    0.74
    TypedDataSet
    0.71
     للاسماء
    0.66
     fieldNum
    0.65
     Roskov
    0.64
    AnchorStyles
    0.63
    fortawesome
    0.62
     cherchés
    0.62
    Autoritní
    0.62
    NewUrlParser
    0.61
    Activations Density 0.152%

    No Known Activations