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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8254
    Prev
    Next
    INDEX
    Explanations

    terms related to backend processing and data structure in programming

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

    Preceding a slash or a colon

    np_acts-logits-general · gemini-2.0-flash

    file paths and technical terms

    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
     mergeFrom
    -1.14
     ModelExpression
    -1.06
    SourceChecksum
    -1.06
     Roskov
    -1.05
     &___
    -1.04
    LookAnd
    -0.97
    новниш
    -0.94
     >=",
    -0.90
    AddTagHelper
    -0.89
    ']")
    -0.87
    POSITIVE LOGITS
    .
    0.62
    ,
    0.50
    core
    0.42
    :
    0.41
    /
    0.38
     gidi
    0.38
     însă
    0.37
    Handlung
    0.35
    HideInInspector
    0.35
     principle
    0.35
    Activations Density 0.169%

    No Known Activations