© 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. 8104
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to database insertion operations

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

    the word "insert" or "INSERT" in various contexts (database queries, code, 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
     pitié
    -0.42
     يتيمه
    -0.39
     chemise
    -0.37
     siena
    -0.36
     niedersachsen
    -0.35
     McAllister
    -0.35
    Etape
    -0.35
     Fland
    -0.35
     westfalen
    -0.34
    gsmål
    -0.34
    POSITIVE LOGITS
     insertion
    0.84
     Insertion
    0.82
    Inserting
    0.80
     insertions
    0.79
     inserted
    0.76
    insertion
    0.76
     inserting
    0.74
     inser
    0.71
    Insertion
    0.71
     into
    0.71
    Activations Density 0.348%

    No Known Activations