© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14554
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hardware register names and memory addresses in C code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLT
    -0.56
     GK
    -0.54
     TNT
    -0.52
     ORD
    -0.51
     CDN
    -0.50
    TNT
    -0.50
    ScopeManager
    -0.49
     IPT
    -0.49
    PRP
    -0.49
     AppCompatTheme
    -0.48
    POSITIVE LOGITS
     bit
    0.66
     bits
    0.53
     programmable
    0.52
    RESERVED
    0.52
     reserved
    0.51
     firmware
    0.50
     Reserved
    0.48
     register
    0.47
    firmware
    0.46
     hardware
    0.46
    Activations Density 3.101%

    No Known Activations