© 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. 13639
    Prev
    Next
    INDEX
    Explanations

    comment blocks in code

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

    "/**" in code comments

    np_acts-logits-general · gemini-2.0-flash

    code comments and docstrings

    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
    AsUp
    -0.90
    oredCriteria
    -0.68
    wußt
    -0.65
     ligiloj
    -0.63
    bootstrapcdn
    -0.63
    LookAnd
    -0.62
     Савезне
    -0.61
    mergeFrom
    -0.61
    новниш
    -0.60
     linkovi
    -0.59
    POSITIVE LOGITS
    ****************
    1.25
    ************
    1.04
    **************
    1.02
    ***************
    1.02
    ********
    0.98
    ***********
    0.98
    **********
    0.98
    *************
    0.92
    /**
    0.89
    *******
    0.89
    Activations Density 0.026%

    No Known Activations