© 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. 24-GEMMASCOPE-RES-16K
    6. 13707
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and well-being, including the benefits of physical activities and emotional states

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

    "Too" and similar words

    np_acts-logits-general · gemini-2.0-flash

    adding too

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.80
    contentLoaded
    -0.74
    CompleteListener
    -0.69
     kaarangay
    -0.68
    webElementXpaths
    -0.67
     AssemblyCulture
    -0.66
     isInitialized
    -0.66
    Filmografia
    -0.65
     WaitForSeconds
    -0.64
     snippetHide
    -0.64
    POSITIVE LOGITS
     too
    4.20
    too
    3.16
     TOO
    2.60
    Too
    2.60
     Too
    2.56
    TOO
    2.17
     тоже
    2.12
     aswell
    2.10
     also
    1.98
     också
    1.80
    Activations Density 1.301%

    No Known Activations