© 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. 15-GEMMASCOPE-RES-16K
    11. 1417
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to substrates, layers, and fluid systems in the context of engineering or manufacturing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.40
    髦
    -0.36
    ineno
    -0.36
    ombic
    -0.35
     come
    -0.34
     Gre
    -0.34
     concede
    -0.34
     conceded
    -0.33
     disper
    -0.33
     COME
    -0.33
    POSITIVE LOGITS
     ProtoMessage
    0.63
    出版年
    0.52
    httphttps
    0.49
     propOrder
    0.48
     plufieurs
    0.47
    󠁬
    0.46
    :✨
    0.46
    parsedMessage
    0.44
     defStyleAttr
    0.44
     TextInputType
    0.44
    Activations Density 0.769%

    No Known Activations