© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 106047
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to SQL database management systems

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

    database systems and SQL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fordítás
    -0.53
    Дереккөздер
    -0.51
    IContainer
    -0.51
    akana
    -0.45
    σθαι
    -0.44
    Bound
    -0.44
    DockStyle
    -0.43
    ComponentScan
    -0.43
    PageRoute
    -0.43
    mass
    -0.43
    POSITIVE LOGITS
    SqlClient
    0.61
     sqlalchemy
    0.51
     SqlDbType
    0.49
     SQL
    0.48
     DBMS
    0.47
    enderror
    0.47
    DBMS
    0.45
     PostgreSQL
    0.45
    postgresql
    0.44
    SQL
    0.44
    Activations Density 0.063%

    No Known Activations