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. 10268
    Prev
    Next
    INDEX
    Explanations

    terms specific to the Spring Framework and threading concepts 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
     Efq
    -0.74
    TagHelpers
    -0.74
    TagHelper
    -0.69
     duele
    -0.69
    iostream
    -0.65
    ngth
    -0.64
     étoit
    -0.64
     lotus
    -0.63
    ENEFITS
    -0.63
    MessageState
    -0.62
    POSITIVE LOGITS
    springframework
    2.09
    DebuggerNonUser
    1.12
     createSlice
    0.72
    stereotype
    0.71
    contentLoaded
    0.71
    RegressionTest
    0.68
     styled
    0.67
     ControllerBase
    0.65
    لينكات
    0.65
    Einzelnachweise
    0.62
    Activations Density 0.004%

    No Known Activations