© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11399
    Prev
    Next
    INDEX
    Explanations

    concepts related to estimations, significance, and statistical analyses

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

    the verb "is" or "was" in passive voice constructions describing scientific results and findings.

    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
    transQ
    -0.50
     ainfi
    -0.50
     فريبيس
    -0.40
    WithError
    -0.40
    skosten
    -0.39
    Vegeu
    -0.39
    RegressionTest
    -0.38
    resave
    -0.38
    ngOn
    -0.38
    Notae
    -0.38
    POSITIVE LOGITS
     obtained
    1.09
     achieved
    0.98
    obtained
    0.90
     accomplished
    0.89
     accessed
    0.84
     Obtained
    0.84
     ottenuto
    0.79
     handled
    0.79
     attained
    0.77
    achieved
    0.77
    Activations Density 1.122%

    No Known Activations