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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4578
    Prev
    Next
    INDEX
    Explanations

    declarations of public methods and their attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.71
    Autowired
    -0.69
    LookAnd
    -0.64
    싶
    -0.58
    CUSS
    -0.58
    upp
    -0.57
    piram
    -0.56
     Gould
    -0.55
     насељу
    -0.55
    Pautan
    -0.54
    POSITIVE LOGITS
    Override
    0.74
    ngrx
    0.72
     IndexPath
    0.71
    CloseOperation
    0.70
    InjectAttribute
    0.69
     AssemblyCulture
    0.68
    reactivex
    0.62
    toolStripButton
    0.61
     وتسجيلات
    0.61
    avits
    0.59
    Activations Density 0.012%

    No Known Activations