© 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. 2990
    Prev
    Next
    INDEX
    Explanations

    elements related to user management in code, including user properties, actions, and states

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

    Code, game, or system instances

    np_acts-logits-general · gemini-2.0-flash

    programming constructs and objects

    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
     otomatig
    -1.07
    UnsafeEnabled
    -1.03
     autorytatywna
    -0.90
    GEBURTSDATUM
    -0.88
     ujednoznacz
    -0.87
     Савезне
    -0.86
     дописавши
    -0.84
     HasFactory
    -0.83
    XmlAccessorType
    -0.81
    ఔ
    -0.80
    POSITIVE LOGITS
    stretchr
    0.62
     viewDidLoad
    0.52
    apimachinery
    0.51
    mybatisplus
    0.46
     Thị
    0.46
    openqa
    0.45
    dalla
    0.44
    zeitige
    0.44
    MVC
    0.44
    mobileqq
    0.44
    Activations Density 0.747%

    No Known Activations