© 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. 3-GEMMASCOPE-RES-16K
    6. 8774
    Prev
    Next
    INDEX
    Explanations

    words related to causes or explanations

    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
    ſelf
    -0.68
     Houſe
    -0.62
     feroit
    -0.60
     ainfi
    -0.60
     inalámbrica
    -0.59
     desmotivaciones
    -0.59
    ſelves
    -0.56
     nôtre
    -0.55
     queſta
    -0.55
     plegable
    -0.55
    POSITIVE LOGITS
     por
    1.16
     по
    1.09
    по
    0.73
    По
    0.68
    +#+
    0.63
     По
    0.60
     Porter
    0.56
    por
    0.54
     за
    0.52
     ب
    0.51
    Activations Density 0.029%

    No Known Activations