© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1273
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to SQL and database management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeografia
    -0.90
    ---*/
    -0.87
    Personensuche
    -0.85
    posedge
    -0.85
    ListItemIcon
    -0.82
    antMatchers
    -0.78
    SourceChecksum
    -0.76
     autorytatywna
    -0.76
     PLWABN
    -0.75
    Obrázky
    -0.75
    POSITIVE LOGITS
     SQL
    1.30
     Sql
    1.28
    sql
    1.28
     sql
    1.24
     sqlSession
    1.13
    SqlClient
    1.11
    Sql
    1.08
    SQL
    1.04
    SQLException
    0.83
    ql
    0.79
    Activations Density 0.052%

    No Known Activations