Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6906
    Prev
    Next
    INDEX
    Explanations

    references to SQL code and related components

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

    SQL code or syntax

    np_acts-logits-general · gemini-2.0-flash

    sql database syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بوابة
    -0.49
    Datuak
    -0.48
    PreferredItem
    -0.46
    iNdEx
    -0.46
    center
    -0.46
    Meister
    -0.44
     Autorizaciones
    -0.44
    anthe
    -0.44
     Autorisations
    -0.43
    from
    -0.43
    POSITIVE LOGITS
    sql
    2.58
     sql
    2.44
     SQL
    2.14
    SQL
    2.03
     Sql
    2.02
    Sql
    1.98
    SqlClient
    1.31
    ql
    1.14
     mysql
    1.11
    ysql
    1.09
    Activations Density 0.062%

    No Known Activations