© 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. 22-GEMMASCOPE-RES-16K
    6. 7685
    Prev
    Next
    INDEX
    Explanations

    terms related to financial programs and risk assessments

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

    Abbreviations starting with "R"

    np_acts-logits-general · gemini-2.0-flash

    acronyms starting with R

    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
    IsContent
    -0.62
    AccessorTable
    -0.61
    DockStyle
    -0.58
    ContentAsync
    -0.55
    EDEFAULT
    -0.55
     виправивши
    -0.54
     HasFactory
    -0.53
     تضيفلها
    -0.49
    JsonInclude
    -0.47
    makeText
    -0.47
    POSITIVE LOGITS
     RA
    1.16
     Ra
    1.08
     RR
    1.07
     RP
    1.04
     RB
    1.02
     RS
    1.02
     ra
    1.02
     R
    1.02
     RM
    1.01
     RD
    1.01
    Activations Density 2.464%

    No Known Activations