© 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. 5024
    Prev
    Next
    INDEX
    Explanations

    mention of experiments and their effects on memory

    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
     eighty
    -1.35
     seventy
    -1.31
     fifty
    -1.30
     sixty
    -1.27
     ninety
    -1.24
     forty
    -1.23
    fifty
    -1.20
     thirty
    -1.14
    Fifty
    -1.13
    forty
    -1.13
    POSITIVE LOGITS
    第
    0.62
     ½
    0.59
     
    0.55
    GEBURTS
    0.50
     ¾
    0.40
     externi
    0.39
     davon
    0.38
     ¼
    0.36
     &
    0.34
     др
    0.34
    Activations Density 0.949%

    No Known Activations