© 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. 10770
    Prev
    Next
    INDEX
    Explanations

    terms related to strategies and classifications

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

    relating to data, statistics, or genes in tables

    np_acts-logits-general · gemini-2.0-flash

    data, statistics, or categories

    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
    PreferredItem
    -0.77
     pourtant
    -0.72
    EDEFAULT
    -0.72
    Portale
    -0.71
     disambiguazione
    -0.70
     виправивши
    -0.69
    rungsseite
    -0.69
    Хьажоргаш
    -0.69
    ']))
    
    -0.68
    basicConfig
    -0.67
    POSITIVE LOGITS
     sorted
    0.94
     grouped
    0.91
     based
    0.85
     broken
    0.85
     berdasarkan
    0.83
     along
    0.82
     according
    0.81
     beserta
    0.78
     showing
    0.78
     wraz
    0.76
    Activations Density 0.879%

    No Known Activations