© 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. 16-GEMMASCOPE-RES-16K
    11. 4297
    Prev
    Next
    INDEX
    Explanations

    file and document paths or references in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File paths starting with "/"

    np_acts-logits-general · gemini-2.0-flash

    paths and filenames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.75
    DeleteBehavior
    -0.73
     defaultstate
    -0.69
    addCriterion
    -0.64
    %)$
    -0.62
     PyLong
    -0.61
    RTGC
    -0.60
    ItemBackground
    -0.60
    ]")]
    -0.59
     wireType
    -0.58
    POSITIVE LOGITS
     "..\..\..\
    0.74
     "..\..\
    0.68
     Coma
    0.58
     насељу
    0.55
     Ressources
    0.52
    tableFuture
    0.51
    :✨
    0.50
    τηση
    0.50
    Portale
    0.50
    lib
    0.50
    Activations Density 0.304%

    No Known Activations