Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10988
    Prev
    Next
    INDEX
    Explanations

    patterns related to local player interactions in a game context

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

    abbreviations or short codes

    np_acts-logits-general · gemini-2.0-flash

    Yiji, Jijiu, KOF, Jark, transcations

    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
     "..\..\..\
    -0.61
     "..\..\
    -0.57
    jsdelivr
    -0.54
    SequentialGroup
    -0.52
     SwitchCompat
    -0.51
    )|^{
    -0.50
    toggleClass
    -0.50
    webElementXpaths
    -0.49
    monial
    -0.48
     pinulongan
    -0.47
    POSITIVE LOGITS
    eng
    0.66
    iao
    0.56
    ongs
    0.56
    ux
    0.55
    uan
    0.55
    ong
    0.54
     desorption
    0.52
    __":
    0.52
    uo
    0.52
    ang
    0.51
    Activations Density 0.213%

    No Known Activations