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. 18-GEMMASCOPE-RES-16K
    6. 810
    Prev
    Next
    INDEX
    Explanations

    phrases related to scoring and lead changes in competitive sports

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

    before or related to "-ing" endings

    np_acts-logits-general · gemini-2.0-flash

    winning and storms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTDA
    -0.55
    writeFieldEnd
    -0.54
     EconPapers
    -0.53
     незавершена
    -0.53
     Reverso
    -0.51
     trataba
    -0.51
    jgl
    -0.50
    contentLoaded
    -0.49
    neté
    -0.49
     testar
    -0.49
    POSITIVE LOGITS
    UnusedPrivate
    0.68
     romp
    0.62
    XPATH
    0.60
    一路
    0.59
    abestanden
    0.59
     giành
    0.58
    \{\\
    0.56
     winning
    0.56
     ench
    0.55
     clin
    0.54
    Activations Density 0.122%

    No Known Activations