© 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. 40-GEMMASCOPE-RES-16K
    11. 1582
    Prev
    Next
    INDEX
    Explanations

    terms related to machinery and construction processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.44
    lapsingToolbar
    -0.43
    haikusbot
    -0.39
     initComponents
    -0.38
     HasFactory
    -0.37
    aternion
    -0.37
     thiệu
    -0.36
    Népesség
    -0.36
     AppCompatTheme
    -0.36
    ništvo
    -0.36
    POSITIVE LOGITS
     digging
    2.14
     dug
    1.88
     dig
    1.86
     Dig
    1.73
     excavation
    1.73
     digger
    1.71
    Dig
    1.71
     exca
    1.69
     excavated
    1.67
     digs
    1.65
    Activations Density 0.509%

    No Known Activations