© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5974
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures used in coding, particularly in defining types and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.55
    ListItemIcon
    -0.52
     "..\..\..\
    -0.50
     AssemblyCompany
    -0.49
     "..\..\
    -0.49
    tagHelper
    -0.46
    EndInit
    -0.46
     julk
    -0.44
    ModelAttribute
    -0.42
     Nectar
    -0.42
    POSITIVE LOGITS
    djangoproject
    0.76
    fjspx
    0.61
     WaitForSeconds
    0.59
    WriteBarrier
    0.59
    didSet
    0.58
     виправивши
    0.58
    存于互联网档案馆
    0.56
    IntoConstraints
    0.55
    Pautan
    0.55
    őbb
    0.54
    Activations Density 0.265%

    No Known Activations