© 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. 2-GEMMASCOPE-RES-16K
    11. 1025
    Prev
    Next
    INDEX
    Explanations

    code-related terms and constructs, particularly those associated with data structures and programming logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\
    -0.56
     hasattr
    -0.52
    DataSnapshot
    -0.51
     pacchetto
    -0.50
     "..\..\..\
    -0.49
    modelBuilder
    -0.48
    jspx
    -0.47
    vedev
    -0.47
     CreateTagHelper
    -0.47
    gebob
    -0.46
    POSITIVE LOGITS
     esternos
    0.87
    <?
    0.68
     snippetHide
    0.68
    RegressionTest
    0.63
     Winaray
    0.60
    principalTable
    0.60
    })));
    0.57
     otomatig
    0.57
    ')")
    0.56
    )':
    0.56
    Activations Density 0.549%

    No Known Activations