© 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. 35-GEMMASCOPE-RES-16K
    11. 7847
    Prev
    Next
    INDEX
    Explanations

    technical terms related to caching and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.37
     sant
    -0.36
     anatom
    -0.36
     NUKAT
    -0.36
    Portale
    -0.35
     transfieras
    -0.35
     awk
    -0.35
    WebVitals
    -0.35
     Cardinale
    -0.35
     Kamp
    -0.34
    POSITIVE LOGITS
     cache
    2.45
     Cache
    2.17
    cache
    2.11
     caches
    1.98
    Cache
    1.97
     caching
    1.91
     CACHE
    1.89
    CACHE
    1.76
     cached
    1.73
    缓存
    1.68
    Activations Density 0.565%

    No Known Activations