© 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. 11240
    Prev
    Next
    INDEX
    Explanations

    quantitative metrics related to data transmission and performance evaluation

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

    followed by "of" that quantify something

    np_acts-logits-general · gemini-2.0-flash

    rate, ratio, levels, value

    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
     Audiodateien
    -0.61
     GoogleFonts
    -0.58
     Khas
    -0.56
    kkelijk
    -0.56
    FormTagHelper
    -0.56
     TextAppearance
    -0.56
     snippetHide
    -0.54
    horst
    -0.53
    demies
    -0.53
    fusc
    -0.53
    POSITIVE LOGITS
     rate
    1.11
     levels
    1.11
     level
    1.05
     ratio
    0.98
     rates
    0.92
     rating
    0.84
    levels
    0.84
    rate
    0.81
     LEVELS
    0.79
     value
    0.78
    Activations Density 1.324%

    No Known Activations