Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8325
    Prev
    Next
    INDEX
    Explanations

    keywords and modifiers related to programming constructs and definitions, particularly in the context of languages like Swift or Kotlin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.66
     betweenstory
    -0.65
    adaptiveStyles
    -0.59
    WriteLiteral
    -0.53
     useAppContext
    -0.52
    ----</
    -0.51
    <?
    -0.50
    FieldBuilder
    -0.50
    -------
    -0.49
     invokingState
    -0.49
    POSITIVE LOGITS
    IBOutlet
    0.60
    ErrUnexpectedEOF
    0.58
    IBAction
    0.53
     extern
    0.53
    extern
    0.49
     crossorigin
    0.47
    DockStyle
    0.45
    Extern
    0.45
     atomic
    0.44
    FXML
    0.44
    Activations Density 0.197%

    No Known Activations