© 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. 11335
    Prev
    Next
    INDEX
    Explanations

    variables and parameters related to equations and functions in programming or mathematical contexts

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

    Mathematical or programming expressions

    np_acts-logits-general · gemini-2.0-flash

    code-like numbers and variable assignments

    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
     hear
    -0.61
     hears
    -0.58
    FormsModule
    -0.56
    hear
    -0.56
    balleur
    -0.56
     dụ
    -0.55
     temptation
    -0.55
    DockStyle
    -0.51
     <<=
    -0.51
     hearing
    -0.49
    POSITIVE LOGITS
    )/
    0.90
    ])/
    0.63
    ]/
    0.63
    ))/
    0.59
    )/(
    0.55
    wapV
    0.52
    Personensuche
    0.52
     Signalez
    0.51
     Theory
    0.51
    "]/
    0.51
    Activations Density 0.590%

    No Known Activations