© 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. 12-GEMMASCOPE-RES-16K
    11. 5187
    Prev
    Next
    INDEX
    Explanations

    references to return or coming back, especially in the context of people's actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.56
     Bruins
    -0.48
    rungsseite
    -0.47
     initComponents
    -0.44
     Mediation
    -0.44
     drifts
    -0.43
    AntiForgeryToken
    -0.43
     Normdatei
    -0.41
     peering
    -0.41
     TestBed
    -0.41
    POSITIVE LOGITS
     pulang
    0.51
    帰
    0.51
     regresar
    0.49
     regresó
    0.49
     returning
    0.48
    AnimationsModule
    0.46
     returned
    0.44
    Returning
    0.44
    帰って
    0.42
     return
    0.42
    Activations Density 0.484%

    No Known Activations