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. 22-GEMMASCOPE-RES-16K
    6. 8076
    Prev
    Next
    INDEX
    Explanations

    phrases related to employment and job roles

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

    "full" followed by a time period or job

    np_acts-logits-general · gemini-2.0-flash

    full time

    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
    WaitGroup
    -0.74
     Theſe
    -0.66
    出版年
    -0.62
    ReusableCell
    -0.62
    ]")]
    -0.61
     IBOutlet
    -0.59
    Slf
    -0.59
     UnityEngine
    -0.59
     Jefus
    -0.56
     verſ
    -0.56
    POSITIVE LOGITS
     full
    3.05
    full
    2.59
     Full
    2.47
    Full
    2.45
     FULL
    2.14
    FULL
    2.13
    フル
    1.63
     peł
    1.60
     Voll
    1.54
     penuh
    1.52
    Activations Density 0.351%

    No Known Activations