© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13231
    Prev
    Next
    INDEX
    Explanations

    phrases that describe methods or approaches allowing for specific outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.59
    BufferException
    -0.58
    OrBuilder
    -0.57
     Coss
    -0.56
    Autoritní
    -0.53
    naphthal
    -0.50
     AssemblyCompany
    -0.49
    ≻
    -0.48
     hang
    -0.47
     Vide
    -0.46
    POSITIVE LOGITS
     Dadurch
    0.43
     thereby
    0.40
     minimize
    0.40
     flexibility
    0.37
    ThroughAttribute
    0.36
     maximize
    0.36
     informée
    0.36
     allowing
    0.35
     minimizes
    0.35
     bankası
    0.34
    Activations Density 0.331%

    No Known Activations