© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9492
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to caching, memory, and debugging

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

    HTML/XML cache configuration parameters and technical cache-related documentation.

    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
    :✨
    -0.41
    WebVitals
    -0.39
    šť
    -0.35
    PullParser
    -0.33
     Compagn
    -0.33
     ſou
    -0.33
     DialogResult
    -0.32
     giuri
    -0.32
    菌
    -0.32
    endmodule
    -0.31
    POSITIVE LOGITS
     cache
    1.95
     Cache
    1.75
     caching
    1.64
     caches
    1.63
    cache
    1.63
     CACHE
    1.57
    Cache
    1.55
    CACHE
    1.44
     cached
    1.41
    缓存
    1.39
    Activations Density 0.542%

    No Known Activations