© 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. 13571
    Prev
    Next
    INDEX
    Explanations

    moments of significant beginnings or changes

    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
    NullCheck
    -0.59
    شهاد
    -0.59
     zuletzt
    -0.57
    errHandler
    -0.54
     показа
    -0.51
     provato
    -0.50
    glClear
    -0.50
    dymyr
    -0.50
     Schach
    -0.49
     ThemeData
    -0.49
    POSITIVE LOGITS
     begins
    1.16
     begun
    1.07
     began
    1.05
     dimulai
    1.05
     Begins
    1.04
     begin
    1.00
    begins
    1.00
     starts
    1.00
     Began
    0.98
     Begin
    0.95
    Activations Density 0.218%

    No Known Activations