© 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. 3-GEMMASCOPE-RES-16K
    11. 6380
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rare" and variations of it

    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
     виправивши
    -0.57
    ollectionView
    -0.56
     onResponse
    -0.55
     never
    -0.55
    NEVER
    -0.53
    蚪
    -0.52
     Normdatei
    -0.49
    never
    -0.47
     invokingState
    -0.47
    dillera
    -0.47
    POSITIVE LOGITS
     rare
    2.45
     Rare
    2.11
    Rare
    1.95
    rare
    1.70
     rarer
    1.64
     RARE
    1.62
     rares
    1.61
     rarest
    1.57
     raro
    1.44
     raras
    1.41
    Activations Density 0.051%

    No Known Activations