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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5510
    Prev
    Next
    INDEX
    Explanations

    code structures related to defining functions and classes

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

    `azure.cli.command_modules.acr`

    np_acts-logits-general · gemini-2.0-flash

    azure cli commands

    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
     BorderLayout
    -0.50
    DoubleQuotes
    -0.49
     OkHttpClient
    -0.41
    textTheme
    -0.40
    jsdelivr
    -0.40
    CodeAnalysis
    -0.39
    PKCS
    -0.38
    nsf
    -0.37
    BorderLayout
    -0.37
    urra
    -0.37
    POSITIVE LOGITS
    WriteTagHelper
    0.78
    Personensuche
    0.78
     otomatig
    0.76
    énario
    0.69
     EconPapers
    0.68
    zzleHttp
    0.68
    PMailer
    0.68
    richTextPanel
    0.67
     صوتيه
    0.65
     esternos
    0.64
    Activations Density 0.210%

    No Known Activations