© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11747
    Prev
    Next
    INDEX
    Explanations

    references to objects and variables within code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -1.06
     betweenstory
    -1.05
    دانشنامهٔ
    -0.99
    IUrlHelper
    -0.96
    NUMX
    -0.94
    ftagPool
    -0.91
     disambiguazione
    -0.89
    VIAF
    -0.86
    uxxxx
    -0.85
     bezeichneter
    -0.83
    POSITIVE LOGITS
    ing
    0.49
    ali
    0.46
     lég
    0.46
    (`${
    0.46
    ure
    0.46
    web
    0.44
    ana
    0.44
     his
    0.43
    </
    0.42
    (`
    0.41
    Activations Density 0.633%

    No Known Activations