© 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. 4862
    Prev
    Next
    INDEX
    Explanations

    instances of object manipulation and state management in code

    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
    providedIn
    -1.02
     esternos
    -0.95
    tagHelperRunner
    -0.94
     Audiodateien
    -0.94
    ➟
    -0.91
    ंदीखरीदारी
    -0.89
     חיצוניים
    -0.89
    GraphicsUnit
    -0.88
     للاسماء
    -0.87
    KommentareTeilen
    -0.86
    POSITIVE LOGITS
    <bos>
    0.77
     and
    0.44
    ,
    0.43
     ranging
    0.38
     even
    0.38
     most
    0.37
     nunc
    0.36
     &
    0.36
     or
    0.35
    -
    0.35
    Activations Density 4.147%

    No Known Activations