Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8672
    Prev
    Next
    INDEX
    Explanations

    references to temporal phrases or expressions related to beginnings and endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.70
    \{\\
    -0.66
    Datuak
    -0.65
     ainfi
    -0.65
     $_(
    -0.65
    Dış
    -0.62
     autorytatywna
    -0.59
    ="@+
    -0.59
     InputDecoration
    -0.58
    addCriterion
    -0.57
    POSITIVE LOGITS
     afterwards
    0.48
     times
    0.47
     throughout
    0.45
     underneath
    0.45
     afterward
    0.42
     superposition
    0.41
    一开始
    0.40
    一開始
    0.40
     Ende
    0.39
     time
    0.38
    Activations Density 0.206%

    No Known Activations