© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3678
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to various subjects

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

    References or citations with numbers

    np_acts-logits-general · gemini-2.0-flash

    medical terms and identifiers

    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
     تضيفلها
    -0.87
    исленность
    -0.72
    帖最后由
    -0.66
    webElementXpaths
    -0.66
    WillAppear
    -0.65
     inilah
    -0.63
    CppMethod
    -0.60
    RegistryLite
    -0.59
    BeginInit
    -0.59
    Naissance
    -0.58
    POSITIVE LOGITS
    ########.
    0.54
    2
    0.54
     ſever
    0.52
    1
    0.52
    3
    0.51
     Reſ
    0.51
    4
    0.51
    0
    0.51
    ècie
    0.50
     Thine
    0.49
    Activations Density 0.600%

    No Known Activations