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. 3-GEMMASCOPE-RES-16K
    6. 16276
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "new" associated with object creation and error handling in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DispatchToProps
    -0.56
    ulemon
    -0.54
    MAXN
    -0.54
     calendriers
    -0.51
    ابراین
    -0.50
    amssymb
    -0.50
     florales
    -0.50
    +'/
    -0.49
     doInBackground
    -0.49
     ZH
    -0.49
    POSITIVE LOGITS
    InjectAttribute
    0.84
     snippetHide
    0.75
     ReSharper
    0.67
     Meksiku
    0.65
    PageFactory
    0.61
    WriteTagHelper
    0.61
    BeginContext
    0.60
    دانشنامهٔ
    0.60
    帖最后由
    0.59
     new
    0.57
    Activations Density 0.101%

    No Known Activations