© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7995
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific codes and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.40
    RegressionTest
    -0.40
    setContentView
    -0.35
    pushFollow
    -0.35
    UVWXYZ
    -0.34
    documentclass
    -0.33
     suspension
    -0.33
     aftermath
    -0.33
    MergeFrom
    -0.32
     compro
    -0.32
    POSITIVE LOGITS
    出版年
    0.66
    InstrumentedTest
    0.63
    weightedMode
    0.62
     ſehr
    0.61
    BibitemShut
    0.59
    ſelben
    0.57
     ſind
    0.56
     zelve
    0.56
    НИК
    0.56
     resourceCulture
    0.56
    Activations Density 0.818%

    No Known Activations