© 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. 38-GEMMASCOPE-RES-16K
    11. 14697
    Prev
    Next
    INDEX
    Explanations

    phrases related to evidence and derived data in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     siquiera
    -0.48
    出版年
    -0.46
    COUVER
    -0.42
    writeFieldEnd
    -0.41
    niająca
    -0.40
    Datuak
    -0.40
    رشف
    -0.39
    RUCT
    -0.38
    TemporalType
    -0.38
     препратки
    -0.38
    POSITIVE LOGITS
     mainly
    3.52
     primarily
    3.41
     Mainly
    3.16
     mostly
    3.16
     chiefly
    3.06
    Mainly
    3.03
    mainly
    3.02
    primarily
    3.02
     principally
    3.00
     predominantly
    2.97
    Activations Density 1.972%

    No Known Activations