© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2113
    Prev
    Next
    INDEX
    Explanations

    terms related to success and performance in various contexts

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

    preceding "dependent/depends/depended"

    np_acts-logits-general · gemini-2.0-flash

    success depends on

    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
    UnusedPrivate
    -0.58
    المناصب
    -0.56
     BorderSide
    -0.53
    })*/
    -0.49
     surla
    -0.49
    __*/
    -0.48
    ]--;
    -0.47
    RSpec
    -0.47
     Skal
    -0.47
    ']))
    -0.47
    POSITIVE LOGITS
     depends
    2.16
     depend
    2.04
     depended
    1.93
     dépend
    1.78
    depends
    1.77
     dependent
    1.75
     Depends
    1.74
     relies
    1.63
     depende
    1.59
     dipende
    1.53
    Activations Density 0.691%

    No Known Activations