© 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. 18-GEMMASCOPE-RES-16K
    11. 367
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to statistics or data metrics, particularly in numerical contexts

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

    Numbers following mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    numbers and numerical sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.75
    BagLayout
    -0.72
    StoryboardSegue
    -0.66
     Hundred
    -0.66
     ostavi
    -0.66
    onAttach
    -0.64
     CreateTagHelper
    -0.64
    ⓧ
    -0.64
    bolista
    -0.62
    tagHelperRunner
    -0.61
    POSITIVE LOGITS
     five
    0.58
     eight
    0.57
    KS
    0.56
     four
    0.56
     ten
    0.53
     cinco
    0.51
    Eight
    0.50
     nine
    0.50
     six
    0.49
    万元
    0.49
    Activations Density 0.670%

    No Known Activations