© 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. 34-GEMMASCOPE-RES-16K
    11. 11312
    Prev
    Next
    INDEX
    Explanations

    time-related phrases and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.47
    مصادر
    -0.44
    SharedCtor
    -0.43
    EndContext
    -0.40
    脚注の使い方
    -0.38
     betweenstory
    -0.37
    ингл
    -0.37
    oa̍t
    -0.36
    tanleria
    -0.36
     препратки
    -0.36
    POSITIVE LOGITS
     left
    1.27
     remaining
    1.15
    remaining
    0.97
     Remaining
    0.96
    left
    0.90
    Left
    0.90
    Remaining
    0.87
     Left
    0.85
     LEFT
    0.84
    LEFT
    0.78
    Activations Density 0.160%

    No Known Activations