© 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
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2981
    Prev
    Next
    INDEX
    Explanations

    references to columns in data tables or databases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kele
    -0.45
    舺
    -0.43
     consciousness
    -0.43
     Aisha
    -0.43
    setSearch
    -0.42
     Numerade
    -0.42
    tiérrez
    -0.41
    resist
    -0.41
    fq
    -0.40
    vic
    -0.40
    POSITIVE LOGITS
     column
    1.90
     Column
    1.65
     columns
    1.53
    Column
    1.52
     COLUMN
    1.37
     Columns
    1.35
    column
    1.34
     colonne
    1.27
     columna
    1.26
     columnas
    1.23
    Activations Density 0.159%

    No Known Activations