© 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. 22-GEMMASCOPE-RES-16K
    6. 2989
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to programming functions and commands

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

    Code snippets with commas and quotation marks

    np_acts-logits-general · gemini-2.0-flash

    web request parameters

    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
     newArr
    -0.52
     craindre
    -0.47
     remarquer
    -0.46
     defensively
    -0.43
     køb
    -0.42
     dramatique
    -0.42
     promocional
    -0.40
    NameIn
    -0.39
     продаж
    -0.39
    InOrder
    -0.38
    POSITIVE LOGITS
    principalTable
    0.87
     destination
    0.86
     propOrder
    0.83
     target
    0.82
    doctype
    0.80
     source
    0.78
     type
    0.78
    ChildScrollView
    0.78
     متعلقه
    0.77
    WindowConstants
    0.74
    Activations Density 0.761%

    No Known Activations