© 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. 37-GEMMASCOPE-RES-16K
    11. 1022
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer networking and server functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vertre
    -0.37
    GIVEREF
    -0.33
    ĝis
    -0.30
    vědět
    -0.27
     pos
    -0.26
     đạo
    -0.26
    DockStyle
    -0.26
    ****/
    -0.25
    pos
    -0.25
     fidu
    -0.25
    POSITIVE LOGITS
     CPU
    1.36
     performance
    1.15
     throughput
    1.14
    CPU
    1.14
     cpu
    1.13
     latency
    1.08
     bottleneck
    1.02
     bandwidth
    1.01
    performance
    1.00
    cpu
    0.98
    Activations Density 1.118%

    No Known Activations