© 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. 1-GEMMASCOPE-RES-16K
    11. 3171
    Prev
    Next
    INDEX
    Explanations

    the word "right" and its contextual usage in determining correctness or appropriateness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isContained
    -0.57
     Comprometido
    -0.55
     становника
    -0.54
    writeField
    -0.53
    principalColumn
    -0.52
    InjectAttribute
    -0.51
     GetEnumerator
    -0.49
    haikusbot
    -0.49
     intStringLen
    -0.49
    帖最后由
    -0.48
    POSITIVE LOGITS
     appropriate
    0.63
     richtigen
    0.63
     juiste
    0.62
     giusti
    0.57
     proper
    0.55
     ideal
    0.54
     passende
    0.53
     riktig
    0.53
     giusta
    0.53
     rätt
    0.52
    Activations Density 0.192%

    No Known Activations