© 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. 31-GEMMASCOPE-RES-16K
    11. 2630
    Prev
    Next
    INDEX
    Explanations

    SQL statements related to data manipulation and retrieval

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

    SQL database query syntax and structure.

    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
     Handeln
    -0.39
     Publikum
    -0.36
     muerto
    -0.35
     Erwachsenen
    -0.35
     Ciencia
    -0.35
     realizacji
    -0.34
     Rivas
    -0.34
     Männern
    -0.34
    rzez
    -0.34
    inerja
    -0.34
    POSITIVE LOGITS
    httphttps
    0.78
    QMetaType
    0.68
     QuickBooks
    0.67
    WriteTagHelper
    0.62
    Personendaten
    0.59
    ValueStyle
    0.57
     Sage
    0.56
     Roskov
    0.55
     Accounting
    0.53
    VYMaps
    0.53
    Activations Density 0.149%

    No Known Activations