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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14442
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.73
     мәкал
    -0.52
    endphp
    -0.51
    bootstrapcdn
    -0.45
     campamento
    -0.45
     Dostupné
    -0.45
    GRect
    -0.44
     tkinter
    -0.43
    Trichloroethane
    -0.42
    balleur
    -0.42
    POSITIVE LOGITS
    Autowired
    2.11
    IBOutlet
    1.31
    FXML
    0.98
     IBOutlet
    0.95
    SerializeField
    0.92
    InjectMocks
    0.89
    BindView
    0.87
    InjectAttribute
    0.71
    MockBean
    0.70
    Inject
    0.66
    Activations Density 0.031%

    No Known Activations