© 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. 27-GEMMASCOPE-RES-16K
    11. 9411
    Prev
    Next
    INDEX
    Explanations

    phrases concerning interpersonal relationships and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollectionView
    -0.59
    sizeCache
    -0.58
     dezelve
    -0.48
     onAnimation
    -0.47
    flé
    -0.44
    InputTagHelper
    -0.43
    ]")]
    -0.43
     ſche
    -0.43
    BufferException
    -0.42
     nakalista
    -0.42
    POSITIVE LOGITS
     fellow
    0.69
     neighbours
    0.58
     colleagues
    0.56
     neighbors
    0.54
     peers
    0.51
     strangers
    0.50
     sesama
    0.49
     counterparts
    0.48
     kindred
    0.48
    fellow
    0.47
    Activations Density 0.333%

    No Known Activations