© 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. 24-GEMMASCOPE-RES-16K
    11. 2147
    Prev
    Next
    INDEX
    Explanations

    terms related to data types and field definitions in programming contexts

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

    "uint" or "u" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    unsigned integer data types

    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
    complexContent
    -0.58
    verwijspagina
    -0.57
    ฒ
    -0.53
     twee
    -0.50
    PullParser
    -0.50
    EndProject
    -0.49
     four
    -0.49
    artifactId
    -0.49
    DrawerToggle
    -0.49
     BIBSYS
    -0.47
    POSITIVE LOGITS
    3
    0.77
     Thirty
    0.73
    MLLoader
    0.69
    Thirty
    0.67
    mybatisplus
    0.66
    thirty
    0.66
     initComponents
    0.63
    ۱۶
    0.58
     thirty
    0.58
     Sixteen
    0.58
    Activations Density 0.254%

    No Known Activations