© 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. 10-GEMMASCOPE-RES-16K
    11. 6296
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts that challenge misconceptions or present alternative perspectives on reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.60
    ApiProperty
    -0.49
    ExecuteReader
    -0.49
    SharedDtor
    -0.45
    providedIn
    -0.45
    Dichloropropane
    -0.45
     noDo
    -0.44
    windowFixed
    -0.44
    Rhestr
    -0.43
    skjaer
    -0.42
    POSITIVE LOGITS
     egentligen
    0.96
    本当は
    0.94
     Actually
    0.91
    Actually
    0.86
     actually
    0.85
    actually
    0.84
     sebenarnya
    0.82
     ACTUALLY
    0.78
    实际上
    0.76
     egentlig
    0.76
    Activations Density 0.567%

    No Known Activations