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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8734
    Prev
    Next
    INDEX
    Explanations

    references to significant life events and transitional periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ถึง
    -0.51
     Simple
    -0.48
    Simple
    -0.46
    gena
    -0.44
     längre
    -0.43
    quelize
    -0.43
    Basta
    -0.43
    worpen
    -0.43
    DAILY
    -0.43
    omoto
    -0.43
    POSITIVE LOGITS
    parsedMessage
    1.07
    发表于
    0.71
    mybatisplus
    0.68
     insuffisamment
    0.67
    SharedCtor
    0.67
    saraba
    0.65
     ProtoMessage
    0.65
    TagMode
    0.61
     useRouter
    0.61
    GRANTED
    0.61
    Activations Density 0.227%

    No Known Activations