© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 561
    Prev
    Next
    INDEX
    Explanations

    data structure-related terms, particularly focusing on lists, maps, and collections

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

    Java collections: ArrayList, HashMap, or HashSet

    np_acts-logits-general · gemini-2.0-flash

    java collection declarations with generics

    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
    ])))
    -0.65
    __(/*!
    -0.61
    তথ্যসূত্র
    -0.59
     ***!
    -0.58
    ])),
    -0.58
     MainAxisSize
    -0.57
     consultato
    -0.57
    ]),
    
    -0.56
    matchCondition
    -0.56
    interopRequire
    -0.55
    POSITIVE LOGITS
    <
    1.48
     <
    0.91
    <>
    0.86
    \<
    0.80
    <{
    0.78
    <>(
    0.72
    <?
    0.71
    <\
    0.69
    $<
    0.68
    <>();
    0.68
    Activations Density 0.138%

    No Known Activations