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. 13-GEMMASCOPE-RES-16K
    6. 4531
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Act" in the context of regulations or legislation, as well as detecting the presence of the <bos> token indicating the start of a new text segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.59
     getItemCount
    -0.56
    EDEFAULT
    -0.55
     оригіналу
    -0.54
     betweenstory
    -0.54
     bal
    -0.51
     me
    -0.50
     II
    -0.49
    avedra
    -0.49
     Bal
    -0.48
    POSITIVE LOGITS
     Diſ
    0.90
     deſt
    0.82
    RenderAtEndOf
    0.81
     pleaſure
    0.78
     հղումներ
    0.77
     raiſ
    0.75
     EconPapers
    0.72
     ſeveral
    0.72
     reaſon
    0.72
     ſen
    0.72
    Activations Density 0.069%

    No Known Activations