© 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. 31-GEMMASCOPE-RES-16K
    11. 2724
    Prev
    Next
    INDEX
    Explanations

    phrases indicating qualities or characteristics of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sentences that begin with "It's a" followed by an adjective describing something.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    municipi
    -0.52
     noDo
    -0.36
     rekke
    -0.34
    protoc
    -0.33
     OFDb
    -0.33
    parsedMessage
    -0.32
     propOrder
    -0.32
     berikutnya
    -0.32
     ๆ
    -0.31
     række
    -0.31
    POSITIVE LOGITS
     mistake
    0.73
     coincidence
    0.72
     moot
    0.64
     dilemma
    0.62
     question
    0.62
     paradox
    0.62
     questão
    0.61
     misconception
    0.61
     fact
    0.60
     shame
    0.60
    Activations Density 0.291%

    No Known Activations