© 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. 3-GEMMASCOPE-RES-16K
    11. 6473
    Prev
    Next
    INDEX
    Explanations

    instances of the word "real."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.41
    hagy
    -0.39
    chetto
    -0.36
     ItemStack
    -0.35
    ggiato
    -0.34
     Utilizing
    -0.33
    ESTR
    -0.33
    EndContext
    -0.32
    åg
    -0.31
     grundsätzlich
    -0.31
    POSITIVE LOGITS
     real
    3.97
    real
    3.02
     REAL
    2.61
     reales
    2.48
    Real
    2.48
     réelle
    2.47
     réel
    2.45
    REAL
    2.41
     реаль
    2.41
     Real
    2.36
    Activations Density 0.060%

    No Known Activations