© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11615
    Prev
    Next
    INDEX
    Explanations

    references to the structure and operations of a Fragment in Android programming

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

    Code snippets and legal text fragments

    np_acts-logits-general · gemini-2.0-flash

    fragment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -0.55
    HttpConnection
    -0.51
     ringtones
    -0.45
    fection
    -0.45
    匀
    -0.44
     ring
    -0.44
    cheon
    -0.43
     resourceCulture
    -0.43
     Riz
    -0.42
     conversions
    -0.42
    POSITIVE LOGITS
     Fragment
    1.33
     fragment
    1.30
    Fragment
    1.29
    fragment
    1.22
     fragments
    1.07
     frag
    1.05
     Fragments
    1.04
     FRAG
    1.03
    FRAGMENT
    1.00
    Fragments
    0.96
    Activations Density 0.069%

    No Known Activations