© 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. 10884
    Prev
    Next
    INDEX
    Explanations

    semicolons and parentheses in code-related syntax

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

    variable and class declarations in code with specific naming patterns.

    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
     EconPapers
    -0.36
    JspWriter
    -0.36
     referrerpolicy
    -0.33
     getC
    -0.32
     '\\;'
    -0.31
     ujednoznacz
    -0.31
    帖最后由
    -0.29
     '
    
    -0.29
    TAWA
    -0.29
    RTSN
    -0.29
    POSITIVE LOGITS
     surla
    0.60
    Personendaten
    0.59
    CrossRef
    0.57
    出版年
    0.55
    etcode
    0.54
    Geplaatst
    0.53
     ProtoMessage
    0.52
     kapture
    0.52
     pleaſure
    0.51
     planification
    0.51
    Activations Density 0.293%

    No Known Activations