Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11185
    Prev
    Next
    INDEX
    Explanations

    financial metrics and analysis within stock market discussions

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

    Followed by a number or math symbol

    np_acts-logits-general · gemini-2.0-flash

    exercises

    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
     Roskov
    -0.58
     censiti
    -0.55
    WithIOException
    -0.51
     zvuky
    -0.48
    __()
    -0.47
    borderSide
    -0.46
    OTHERS
    -0.45
     Gens
    -0.45
     dolayı
    -0.45
    Сюжет
    -0.44
    POSITIVE LOGITS
     Exercise
    1.26
     exercise
    1.24
     exercises
    1.15
    Exercise
    1.15
    exercise
    1.12
     Exercises
    1.06
     EXERCISE
    1.01
    Exercises
    0.97
     Chapter
    0.96
     Übung
    0.96
    Activations Density 0.504%

    No Known Activations